See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/372658193

A review of task scheduling in cloud computing based on nature- inspired

optimization algorithm

Article · July 2023

DOI: 10.1007/s10586-023-04090-y(

CITATION READS

1 142

3 authors, including:

K. M. Aslam Uddin
Noakhali Science & Technology University
23 PUBLICATIONS 55 CITATIONS

SEE PROFILE

All content following this page was uploaded by K. M. Aslam Uddin on 27 July 2023.

The user has requested enhancement of the downloaded file.

Cluster Computing
https://doi.org/10.1007/s10586-023-04090-y (0123456789().,-volV)
(0123456789().,-volV)

A review of task scheduling in cloud computing based on nature-

inspired optimization algorithm
Farida Siddiqi Prity1 • Md. Hasan Gazi2 • K. M. Aslam Uddin1

Received: 10 May 2023 / Revised: 30 May 2023 / Accepted: 11 June 2023

 The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2023

Abstract
The advent of the cloud computing paradigm allowed multiple organizations to move, compute, and host their applications
in the cloud environment, enabling seamless access to a wide range of services with minimal effort. An efficient and
dynamic task scheduler is required to handle concurrent user requests for cloud services using various heterogeneous and
diversified resources. Improper scheduling can lead to challenges with under or over-utilization of resources, which could
waste cloud resources or degrade service performance. Nature-inspired optimization techniques have been proven effective
at solving scheduling problems. This paper accomplishes a review of nature-inspired optimization techniques for
scheduling tasks in cloud computing. A novel classification taxonomy and comparative review of these techniques in cloud
computing are presented in this research. The taxonomy of nature-inspired scheduling techniques is categorized as per the
scheduling algorithms, nature of the scheduling problem, type of tasks, the primary objective of scheduling, task-resource
mapping scheme, scheduling constraint, and testing environment. Additionally, guidelines for future research issues are
also provided, which should undoubtedly benefit researchers and practitioners as well as open the door for newcomers
eager to pursue their glory in the field of cloud task scheduling.

Keywords Cloud computing
Resource
Task scheduling
Nature-inspired optimization
Taxonomy

1 Introduction govern the utilization of cloud resources while assuring

appropriate, reliable, and adaptable hardware and software
The ever-expanding scope of the transnational corporate that optimizes costs. The early phases of preparing should
atmosphere has prompted the establishment of sophisti- include developing the cloud deployment approach to the
cated technology to handle it [1]. One such innovation that management of clouds [5, 6]. Due to the low probability of
can expedite software deployment processes and save time infrastructure breakdowns in the cloud, servers are con-
and effort is cloud computing [2]. Cloud computing is the sistently and widely accessible. Cloud computing allows
practice of accessing and conserving information and numerous individuals to utilize various applications effi-
applications via the internet rather than locally stored ciently and at a lower cost due to the collaboration of
systems at the consumer’s disposal [3, 4]. It uses distant shared infrastructures [7].
servers connected to the internet to store, administer, and In cloud computing, a scheduler (broker) is designed to
provide online access to information. Organizations must identify possible approaches for allocating a collection of
establish sophisticated cloud management to manage and readily accessible scarce resources to new applications to
maximize scheduling targets such as makespan, computa-
tional cost, monetary cost, reliability, availability, resource
& K. M. Aslam Uddin utilization, response time, energy consumption, etc. [8, 9].
aslam@nstu.edu.bd
The scheduler devises strategies for allocating the proper
1
Department of Information and Communication Engineering, assignments to constrained resources to maximize
Noakhali Science and Technology University, scheduling outcomes [10]. The scheduling algorithm aims
Noakhali 3814, Bangladesh to decide which task will be carried out based on which
2
High Court Division, Supreme Court of Bangladesh, resource [11]. This approach encourages accessibility to
Dhaka 1000, Bangladesh

123
 Cluster Computing

the collaborative resource stream while providing the 7DAs and exhaustive algorithms [16–19]. Meta-heuristic
appropriate consumers with a QOS assurance. The primary algorithms are classified into nature-inspired and non-na-
objective of a novel scheduling approach is to determine ture-inspired [20]. Numerous study findings show that
the best combination of resources that can be employed to nature-inspired optimization algorithms produce superior
accomplish an incoming task so that a scheduling algo- scheduling outcomes than conventional and heuristic ones
rithm can be used to maximize a variety of QOS factors, [21, 22]. While numerous nature-inspired optimization
including expenses, makespan, flexibility, trustworthiness, scheduling techniques have been successfully used in
task disapproval proportion, the efficiency of resources, various computing contexts, including grid and clustering
utilization of energy, etc., and meet restrictions, such as the computing, they have yet to be specifically designed for the
deadline and budgetary constraints, etc., to prevent the cloud. As a result, nature optimization algorithms may
issue of load imbalance. The solution to user satisfaction is initially appear inappropriate as a scheduling option for
achieving the intended efficiency, which may be accom- cloud tasks to the general public. Encouraged by this
plished by rendering the primary objective of cloud com- misunderstanding, this study not only offers a systematic
puting services [12]. Today, a wide range of applications overview of scheduling methods used in the cloud envi-
have been developed that employ the scheduling principle, ronment from a nature-inspired perspective but also
including power system management, scheduling of multi- establishes a connection between conventional/heuristic
modal contents on the global web, and electronic circuit scheduling methods and nature-inspired meta-heuristic
board production [13]. ones so that cloud researchers who are still enthusiastic
Task scheduling in cloud computing is a complicated about conventional/heuristic scheduling can transit to
topic that necessitates tackling a number of effectiveness, scheduling based on nature-inspired optimization swiftly.
resource utilization, and workload administration obstacles The purpose of discussing both conventional and heuristic
while additionally considering diverse assets, task depen- algorithms before discussing nature-inspired optimization
dencies, QoS specifications, assurances, and confidentiality algorithms is to clarify the differentiation between them
issues. The majority of task scheduling challenges are easier.
either NP-complete or NP-hard. As a result, it takes a very We are also inspired by ideas from peer surveys in
long time to develop an optimal solution compared to other earlier works of literature. Task scheduling is a crucial
alternatives [14]. There are no particular techniques for component of cloud computing, which aims to increase
obtaining polynomial-time responses to these issues. Tail- VM utilization while lowering data center operating costs,
lard suggested a scenario in which 0.02 to 1.01 percent of leading to appreciable advancements in QoS metrics and
candidate solutions require the total amount of time nec- overall performance. With an effective task scheduling
essary to reach the best solution [15]. This illustration technique, a high number of user requests may be pro-
demonstrates how challenging it can be to identify the cessed appropriately and assigned to suitable VMs, which
optimum solution to a complex situation. Most researchers helps to meet the needs of cloud users and service provi-
have therefore been motivated to pursue an appropriate ders more effectively. We carefully reviewed numerous
scheduling algorithm to identify a quick yet effective nature-inspired scheduling approaches in the literature, and
solution to this scheduling challenge. The cloud service we discovered that most of the studies of literature do not
provider must offer an effective and optimal scheduling cover all the aspects such as QoS-based comparative
procedure that considers a number of factors, including analysis, state-of-the-art, taxonomy, graphical representa-
cost, time, and SLA standards that must be followed as tions, open issues and comparison of simulation tools of
established by the users. task scheduling as shown in Table 1. Because of this,
conducting a thorough assessment of task scheduling uti-
1.1 Motivation of the research lizing nature-inspired optimization is vitally necessary to
keep up with the field’s continuing, expanding research.
The two primary scheduling techniques modern computer
systems use are exhaustive algorithms and Deterministic 1.2 Contributions of the present study
Algorithms (DAs) [16]. In terms of efficiency, DAs are
substantially better than both conventional (exhaustive) Although nature-inspired scheduling methods considerably
and heuristic methods for scheduling problems. However, impact cloud services, essential methodologies and back-
DAs have two key drawbacks: first, they were designed to grounds of this sector still need to be thoroughly and
handle some data distributions, and second, only some DAs methodically evaluated. As a result, this study aims to
can handle complex scheduling issues. Meta-heuristic compare the prior strategies and assess and critique current
algorithms, also known as approximation algorithms, use cloud scheduling systems in light of nature-inspired algo-
iterative techniques to obtain optimal solutions faster than rithms. A unique classification scheme (taxonomy) and a

123
Cluster Computing

Table 1 Comparison between existing works and the present study

Publication Taxonomy State-of-the- QoS-based comparative Graphical Open Comparison of simulation
art analysis representations issues tools

[23] No No No No No No
[24] Yes Yes No No Yes No
[25] No Yes No No Yes No
[26] Yes Yes No No Yes No
[27] Yes No Yes No No Yes
Present Yes Yes Yes Yes Yes Yes
Study

thorough analysis of contemporary nature-inspired dependent vs. sequence-independent. Scheduling problems

scheduling approaches in cloud computing are provided. are typically distinguished from one another and described
The effectiveness of existing techniques is evaluated based using these limitations. All scheduling issues discussed in
on qualitative QoS parameter-based criteria. The compar- [28] have been explained using a three-fold notation. In
ison of numerous simulation tools frequently used in the this approach, a single or parallel machine designates the
cloud is also presented. Through extensive investigation machine type, sequence-dependent or sequence-indepen-
and discussion, results related to the pertinent aspects are dent specifies the processing features and limitations, and
validated. Finally, research issues are compiled to create a makespan indicates the measure’s value. According to the
research roadmap that could include potential future study length of the scheduling time, the schedule was divided
areas and existing trends. into four categories [29]: short-range, middle-range, long-
range, and reactive control/scheduling.

2 Categorization of cloud task scheduling 2.2 Heuristics scheduling

schemes
Heuristic algorithms vary in performance depending on the
Cloud task scheduling scheme has been divided into three problem they are used for; although they work well for
groups: traditional scheduling, heuristics scheduling, and some situations, they struggle with others. Heuristics typ-
meta-heuristics scheduling. This section has compared the ically deliver a precise response in a reasonable amount of
traditional and heuristics strategies and evaluates and time for a particular type of problem, but they need to
assesses the cloud computing system in light of nature- improve when it comes to challenging optimization prob-
inspired optimization algorithms. lems. Numerous heuristic techniques have been developed,
such as Min-Min [30], Max–Min [30], First Come First
2.1 Traditional scheduling Serve (FCFS) [31], Shortest Job First (SJF) [32], Round
Robin (RR) [33], Heterogeneous Earliest Finish Time
Scheduling can be defined as assigning tasks to a set of (HEFT) [34], Minimum Completion Time (MCT) [35], and
provided machines under the constraints of objective Sufferage [36] in cloud environments to address the
function optimization. The scheduling challenge is called a scheduling issues relating to workflow and independent
single-processor scheduling issue when only one machine tasks/applications.
exists. The scheduling issue is seen as a multiprocessor In the Min-Min heuristics algorithm, the shortest task
scheduling when more than one machine is involved. that can be completed in the shortest amount of time is
Based on resource consumption costs, makespan, load chosen from among all tasks provided, and it is mapped to
balancing, and QoS and its variants, scheduling algorithm a virtual machine that will take the shortest amount of time
performance can be measured. In the context of traditional to complete. When all tasks are successfully scheduled, the
scheduling, a hierarchy of difficulties was established procedure is repeated, lengthening the overall makespan as
through numerous investigations [28, 29] concerning the each task’s completion time lengthens. Large jobs must
characteristics of tasks (i.e., weight, due date, release date, wait until smaller ones are completed before being handled
and processing time), machines (i.e., single or multiple), as by this method, which handles minor chores efficiently.
well as many other details, such as online vs. offline, batch This approach dramatically increases system throughput
vs. non-batch, precedence vs. non-precedence, sequence- overall; however, heavy workloads may cause a starvation

123
 Cluster Computing

problem. Chen et al. [37] and Amalarethinam and Kavitha 3 Nature-inspired meta-heuristics
[38] used Min-Min in their proposed work. A set of issues, scheduling
such as slow task execution, difficulties in the deadline, and
priority problems, arise during the execution of the Min- Nature-inspired algorithms are optimization methods that
Min algorithm. The max–Min algorithm created the prob- handle challenging optimization issues by emulating the
lem of potential resource over-utilization and under-uti- behavior of natural systems [54]. These algorithms effec-
lization in [39] and [40]. Non-continuous monitoring of tively locate optimal solutions for multi-dimensional and
nodes, load imbalance, cost, and time overheads due to multi-modal issues. This paper conducts a schematic
unmanaged communication and storage, and static task review of the nature-inspired optimization techniques of
scheduling problems are introduced while implementing task scheduling in the cloud computing application.
Heterogeneous Earliest Finish Time (HEFT) algorithms
[41, 42]. SJF can not solve the problem of starvation and
load imbalance [43–45]. Round Robin needs to improve its 4 Taxonomy of nature-inspired task
ability to balance the load [46, 47]. Sufferage performs scheduling optimization algorithm
flawlessly in many situations; however, this technique has in cloud computing
drawbacks if numerous tasks have identical suffrage values
[48]. In this scenario, the first arriving task is chosen and A novel, rigorous taxonomy is presented in Fig. 1 using a
run without considering other tasks, which may lead to a number of principal methodologies used in the literature to
starving problem. more thoroughly and clearly comprehend the nature-in-
spired task scheduling approaches in cloud computing.
2.3 Meta-heuristic scheduling This taxonomy divides the methods into seven main divi-
sions based on the type of scheduling algorithm (sched-
Due to their efficiency in resolving complex and extensive uler), nature of the scheduling problem, nature of the task,
computational challenges, meta-heuristic algorithms have primary objectives of scheduling, task-resource mapping
significantly increased in popularity. Task scheduling is schemes, scheduling constraints, and testing environment.
explained by applying heuristic and meta-heuristic meth-
ods to obtain optimal or nearly optimal solutions because 4.1 Scheduling algorithm
traditional methods frequently fail to comprehend situa-
tions to their optimality. Heuristic solutions frequently Nature-inspired scheduling algorithms can be divided into
become caught in a local minima dilemma, and meta- four major categories [55] such as:
heuristic algorithms are the most effective way to escape
• Evolutionary-based
this condition, as mentioned in [24, 26]. Meta-heuristic
• Swarm-based
algorithms efficiently explore the search space to find a
• Physics-based
sub- or near-optimal solution to NP-complete problems. It
• Hybrid approaches
also doesn’t depend on the problem being solved; it typi-
cally uses approximation rather than determinism. Because This study has discussed various algorithms of these
of their intuitive independence from the problem to be four categories of nature-inspired optimization algorithms
addressed, meta-heuristic algorithms are valuable for for task scheduling in cloud computing. Figure 2 illustrates
tackling problems in various domains with highly accept- the overall summary of all the nature-inspired optimization
able performance. Researchers have systematically evalu- algorithms discussed in this section.
ated the application of meta-heuristic algorithms on
scheduling features in cloud and grid settings [49–52]. 4.1.1 Evolutionary-based algorithm
Meta-heuristic techniques are frequently employed as very
efficient solutions to NP-hard optimization issues. Meta- The principles of natural evolution serve as the foundation
heuristic algorithms are classified into two types [53]: for evolutionary approaches [56]. An initially produced
• Nature-inspired population that evolved over several generations serves as
• Non-nature-inspired. the basis for the search procedure. The best individuals are
constantly brought together to create the next generation,
one of these approaches’ most vital points. As a result, the
population can be improved over several generations.
Genetic Algorithm (GA) [57], Memetic Algorithm (MA)
[58], Evolution Strategy (ES) [59], Probability-Based

123
Cluster Computing

Fig. 1 Taxonomy of nature-

inspired task scheduling Evolutionary
approaches Swarm-based
Scheduling
Physics-based
algorithm

Hybrid

Single objective
Nature of
scheduling problem
Multi objective

Independent

Type of task Workflow

Makespan

Security

Reliability

Cost
Nature-inspired
task scheduling Primary objective Load balancing
of scheduling
Resource

Rescheduling

Energy

Static

Task resource Dynamic

mapping scheme
AI-based

Prediction

Deadline
Scheduling
constraints
Priority

Budget
Testing environment
Fault tolerance

Incremental Learning (PBIL) [60], Genetic Programming 4.1.1.1 Genetic algorithm The Darwinian notion of
(GP) [61], Lion Optimization Algorithm (LOA) [62], ‘‘survival of the fittest’’ served as the foundation for the
Imperialist Competitive Algorithm (ICA) [63], Sun Flower development of the genetic algorithm (GA), which is bio-
Optimization Alg (SFO) [64], and Biogeography-Based inspired in that fitness is increased through the process of
Optimizer (BBO) [65] are some of the well-known algo- evolution through reproduction [66]. A Genetic Algorithm
rithms. In this section, some evolutionary nature-inspired analyzes new regions of the solution space while utilizing
algorithms that are used in task scheduling of cloud com- the best solutions from completed searches. Chromosomes,
puting are briefly summarized. composed of a collection of components called genes, can
represent any solution to a particular problem. Crossover or

123
 Cluster Computing

Fig. 2 Nature-inspired
optimization algorithms
discussed in the proposed study

mutation operators produce new offspring chromosomes carried out based on the level-wise representation after
once the population has been initialized with randomly tasks have been organized according to the order of their
produced solutions [67]. The generation of the children is workflow level. In reference [78], the authors used cross-
repeated until enough of the best offspring are produced to over and mutation operators. The chromosomes are
find the best outcome. The scheduling problem response depicted as 2D strings in [79] based on the timeframe and
can be expressed using a variety of representation strate- financial constraints. HEFT is paired with a genetic algo-
gies. Some researchers [68] have encoded the solutions rithm [80] to create a scheduling plan. Authors [81] have
using fixed-length binary strings. A chromosomal matrix is suggested two chromosomes: an ordering chromosome that
utilized to depict the mapping of tasks on resources in specifies the execution order following the scientific
direct representation [69–73]. Paper [74] employed the workflow representation and an allocation chromosome
min-min heuristic and minimum execution time to create that contains the assignment of tasks to nodes. A task
the initial population. When populating the population, the scheduling technique based on the Shadow Price-guided
order of the tasks was also considered [74–76], and genetic Genetic Algorithm (SGA) was presented by [82]. The
operations were then used to solve the workflow scheduling DVFS technique is applied to the grid environment to
issue. In [76], Round Robin and best-fit techniques identify reduce energy consumption and maximize makespan [83].
potential solutions for allocating jobs to resources. The authors of [84] describe a multi-agent evolutionary
According to [77], crossover and mutation operations are method for distributing load among virtual computers.

123
Cluster Computing

A VM allocation methodology with appropriate load bal- takes execution time and execution cost parameters into
ancing and system resource utilization is provided by the account for activities that depend on scheduling. In [104],
method utilized by [85]. The migration cost is optimized the authors offered an online scheduler based on the ICA
through elitism selection and tree structure encoding. and established a dependability model for cloud systems.

4.1.1.2 Memetic algorithm Dawkins’ Memetic Algo- 4.1.1.4 Lion optimization algorithm The Lion Optimiza-
rithm (MA) [86] is based on the term meme. Memes are tion Algorithm (LOA) is a meta-heuristic optimization
concepts like rumors and stories that spread across the algorithm inspired by the social behavior of lions. The
community of meme carriers. MAs use a specific local social structure of lions, in which young are born from
search procedure to enhance or improve individual fitness. resident males and females, is called pride. The lion’s
Many issues in the real world have been addressed using territorial defense and territorial takeover behavior have
MA. In [87], the authors used a memetic method to solve a been used to solve optimization problems [105]. The lion’s
hybrid flow shop scheduling problem involving multipro- behaviors of hunting, going toward a safe area, wandering,
cessor activities. Researchers have employed MA to and migration were included by the authors in [106]. The
address the traveling salesperson problem and quadratic proposed work has been contrasted with algorithms for
assignment [88]. The memetic has been used with hill Invasive Weed Optimization (IWO), Biogeography-based
climbing, tabu search, and simulated annealing for task Optimization (BBO), Gravitational Search (GSA), Hunting
scheduling [89, 90]. The best schedule for a workflow Search (HuS), Bat Algorithm (BA), and Water Wave
application running on a multiprocessor system uses MA Optimization (WWO). The simulation outcomes show how
for multiprocessor scheduling [91]. The authors of [92] effective the LOA algorithm is in solving many other
used this algorithm to shorten the schedule. A global search optimization issues.
optimization based on the Particle Swarm Optimization
(PSO) technique produces candidate solutions. 4.1.1.5 Sunflower optimization algorithm The Sunflower
Optimization Algorithm (SFO) is a population-based
4.1.1.3 Imperialist competitive algorithm The mathe- algorithm modeled after a natural process that moves
matical description of the imperialist competition, which sunflowers toward the sun. The SFO is a new meta-
improves optimization outcomes, inspired the Imperialist heuristic algorithm motivated by sunflowers traveling
Competitive Algorithm (ICA) [93]. Imperialism refers to toward the sun while considering neighboring sunflower
using and controlling another nation’s economic, political, pollination. The performance of the current task scheduling
and human resources by direct legislation. Numerous is improved by the Enhanced Sunflower Optimization
academics have used ICA-based optimization techniques to (ESFO) algorithm introduced in the paper [107]. It dis-
address the scheduling issue. An ICA-based technique is covers the best scheduling strategy in polynomial time. An
used for the flow shop scheduling problem [94]. By effective hybrid optimization algorithm named Sunflower
reducing waiting time in [95], identical work is extended to Whale Optimization Algorithm (SFWOA) is proposed in
reduce maximum completion time. In [96], a bi-objective [108]. The authors of the paper [109] suggest an Opposi-
parallel machine scheduling problem with an emphasis on tion-based Sunflower Optimization (OSFO) algorithm
minimizing mean task completion time was addressed. A improve the efficiency of the task schedulers that are
power-aware load balancing technique reduces energy already in use in terms of cost, energy, and makespan.
consumption in cloud computing data centers based on Paper [110] suggests a sunflower optimization algorithm
ICA [97]. A cost-effective resource provisioning mecha- with a sine–cosine algorithm (SFOA-SCA) for enhancing
nism is provided in [98] to assign virtual machines with the effectiveness of load balancing in cloud networks.
reservations on an on-demand basis. Makespan is opti-
mized for independent tasks in grid computing [99] uti- 4.1.2 Swarm-based algorithm
lizing the imperialist competition method. A hybrid
technique is used for job shop scheduling in [100] to Swarm Intelligence (SI) is a relatively recent method of
reduce the makespan. A Gravitational Attraction Search problem-solving that draws its inspiration from the social
(GAS) technique was introduced in [101] and was inte- behavior of insects and other animals and the collective
grated with ICS in a different study to optimize the service intelligence of swarms of biological populations [111]. A
composition problem in cloud computing more quickly. computational and behavioral paradigm called SI uses the
The authors have expanded their work by combining a interplay of small information processing units to address a
PROCLUS classifier with an ICA algorithm to choose the dispersed problem. The most widely used algorithms are
best service provider for particular services [102]. In [103], Particle Swarm Optimization (PSO) [112], Marriage in
authors developed an ICA-based scheduling method that Honey Bees Optimization Algorithm (MBO) [113], Whale

123
 Cluster Computing

Optimization [114], Firefly Optimization [115], Artificial particle across the board for each generation. The position
Bee Colony (ABC) [116], Ant Colony Optimization (ACO) and speed of the particles are initialized before the popu-
[117], Artificial Fish-Swarm Algorithm (AFSA) [118], Bat lation of the particles is created at random [146–150].
algorithm (BA) [119], Cat Swarm Optimization [120], Discrete PSO is paired with the Min-Min approach [151] to
Termite Algorithm [121], Wasp Swarm Algorithm [122], decrease the execution time of scheduling activities on
Monkey Search [123], Wolf Pack Search Algorithm [124], computational grids. A combination of PSO and Gravita-
Bee Collecting Pollen Algorithm (BCPA) [125], Symbiotic tional Emulation Local Search (GELS) will improve the
organism search optimization algorithm [126], Crow utilization of searching space [152]. Tasks are scheduled
Search, Cuckoo Search [127], Dolphin Partner Optimiza- using a Hybrid Particle Swarm Optimization (HPSO) to
tion (DPO) [128], Grey Wolf Search Algorithm [129], reduce turnaround time and increase resource effectiveness
Glow worm optimization [130], etc. In this section, some [153]. In paper [154], Tabu Search (TS) and PSO are
swarm intelligence nature-inspired algorithms that are used combined to use TS to create a local search mechanism.
in task scheduling of cloud computing are briefly PSO reduces the completion time and improves resource
summarized. utilization when paired with another local search approach
called Cuckoo Search [155]. Task scheduling in grid con-
4.1.2.1 Ant colony optimization Marco Dorigo created texts has been done via particle swarm optimization
the ant colony optimization (ACO). The foraging behavior [156, 157]. A PSO-based hyper-heuristic for resource
of several ant species inspired it. The pheromone that the scheduling in the grid context was presented by R. Aron
ants deposit on the ground instructs the other ants to follow et al. [158]. In [159], a load rebalancing algorithm utilizing
the path. Pheromone values are employed to seek solution PSO and the least position value technique is used for task
space, and the ants record their positions and the caliber of scheduling. PSO suggests a Task-based System Load
their solutions to identify an optimum solution [131]. Paper Balancing method (TBSLB-PSO) in [160]. The method
[132] suggests using the ACO technique to specify the task reduces transfer and task execution times. Improved
and resource selection criteria in clusters. The user speci- makespan and resource utilization are found in [161].
fies QoS limitations in [133] to get the appropriate quality Energy consumption is decreased to 67.5% using the par-
for the scheduling workflow. The paper [134] presents an ticle swarm optimized Tabu search mechanism (PSOTBM)
Ant Colony System (ACS)-based workflow scheduling [162].
algorithm that has been enhanced with several additional
features. The ACO algorithm and the knowledge matrix 4.1.2.3 Artificial bee colony optimization The Artificial
notion are combined in [135]. The researchers adopted the Bee Colony (ABC) algorithm is based on how honey bees
ACO approach [136] to track the historical desirability of intelligently forage for food. Dervis Karaboga created this
putting them in the same physical machine. The paper strategy in 2005 to address real-world issues [163]. Every
[137] has developed an ant colony-based energy-efficient bee in a colony cooperates to find food sources, and this
scheduling algorithm. The updated pheromone schemes are knowledge is used to guide decision-making regarding the
presented in [138, 139]. The population is created using the search for space exploration. Numerous combinatorial
concept of biased starting ants from [140], where the problems, including flow shop scheduling [164], on-shop
expected time to complete a task and the standard devia- scheduling [165], project scheduling [166], and traveling
tions of tasks are considered. An infinite number of ants are salesman [167], have been solved using this technique.
employed in [141] for the grid or cloud-based scheduling [168, 169] provide examples of how bee colony opti-
of interdependent jobs or workflows. Researchers in [142] mization is used for task scheduling in distributed grid
suggest independent work scheduling based on the ACO systems. For task mapping on the resources, authors have
approach for cloud computing systems. Based on ACO, used bees’ foraging behavior as a model. The strategy is
workflow scheduling for grid systems is suggested in [143]. described in [170], which also distributes the workload of
The length of the schedule is kept to a minimum, and tests parallel programs across the resources available in grid
with time-varying workflow are run in a grid setting. When computing systems. Load balancing [171, 172] presents
scheduling workflows in hybrid clouds, reference [144] non-preemptive independent task scheduling based on
considers deadline and cost. ABC optimization. Compared to the Min-Min algorithm,
resource utilization is enhanced by an average of 5.0383%
4.1.2.2 Particle swarm optimization Particle swarm opti- when bee colony and PSO are combined [173]. ABC is
mization (PSO) was created by Eberhart and Kennedy integrated with a Memetic method to reduce the makespan
[145] and is based on the social behavior of particles like and balance the load [174]. Many writers have used the
flocking birds. The particles adjust their path based on their ABC algorithm to schedule different tasks in cloud com-
optimal position and the optimal position of the best puting [175, 176]. The ABC algorithm was made possible

123
Cluster Computing

for scheduling dependent tasks in a cloud context by sev- and improve the overall performance of the cloud com-
eral distinctive characteristics, such as modularity and puting system. Mangalampalli et al. created a Multi-ob-
parallelism [177, 178]. Energy-aware scheduling is sug- jective Trust-Aware Scheduler with Whale Optimization
gested by [179] to effectively manage the resources and (MOTSWO) that prioritizes jobs and virtual machines and
improve their usage in the cloud. schedules them to the best virtual resources while con-
suming the least amount of time and energy possible [194].
4.1.2.4 Bat algorithm A swarm-based method called the The task scheduling technique presented by [195] allocates
Bat Algorithm (BA) imitates bats’ echolocation activity tasks to the appropriate VMS based on determining task
[180]. Bats emit a sound pulse, and an echo is created when and VM priorities. It is modeled using the WOA to reduce
nearby objects reflect that sound pulse. Bats use the lag data center energy use and electricity costs. The multi-
time between the signal’s emission and return to determine objective model and WOA are the foundation for the task
the prey’s precise location, distance, and speed. Paper scheduling algorithm proposed in this research, known as
[181] uses the BA algorithm in a cloud context for resource W-Scheduler [196]. To further expand the WOA-based
scheduling, which optimizes the makespan more effec- method’s capacity to find the best solutions, the authors
tively than the GA method. In [182], a hybrid technique for offer Improved WOA for Cloud Task Scheduling (IWC)
BA-Harmony search is suggested for cloud computing [197]. The suggested IWC offers superior convergence
work scheduling. The Gravitational Scheduling Algorithm speed and accuracy in searching for the optimal task
(GSA) [183] is a further extension of BA that considers scheduling plans than the present meta-heuristic algo-
time restrictions and a trust model. This approach chooses rithms, according to simulation-based studies and com-
resources for task mapping based on their trust value. To prehensive IWC implementation. Another IWC has been
reduce execution costs, the Authors used BA to resolve the presented in [198]. The Vocalization of the Humpback
workflow scheduling issue in the cloud [184]. The Whale Optimization Algorithm (VWOA) is used to opti-
approach performs better in terms of processing costs mize task scheduling in a cloud computing environment
comparing the algorithm to the best resource selection [199]. It reduces time, cost, and energy consumption while
algorithm. PSO and the bat algorithm are combined in the maximizing resource use in terms of makespan, cost,
paper [185] for cloud profit maximization. degree of imbalance, resource utilization, and energy
consumption.
4.1.2.5 Cat swarm optimization The author [186] intro-
duced the Cat Swarm Optimization (CSO) algorithm for 4.1.2.7 Firefly algorithm The flashing behavior of fireflies
continuous optimization issues. Based on the social inspired the nature-inspired optimization method known as
behavior of cats, a heuristic algorithm for optimization is the Firefly Algorithm (FA) [200]. A population-based
proposed. It is based on the seeking and tracking behavior algorithm mimics the flashing behavior of fireflies to
modes of cats. CSO is used in the paper [187]. Researchers choose the best answer. An efficient Trust-Aware Task
in [188, 189] provide many modified versions of CSO for Scheduling algorithm using Firefly optimization has been
resolving discrete optimization issues in various fields. For presented in [201], which has shown a significant impact
the zero–one knapsack issue and the traveling salesperson’s over the conventional approaches by minimizing the
problem, DBCSO [190] is a binary variant of CSO. In makespan, availability, success rate, and turnaround effi-
cloud computing, CSO has been utilized to address the ciency. An acceptable improvement for makespan and
scheduling of workflows while considering single and resource utilization using the FA has been presented in
multiple objectives [191]. Makespan, computation [202]. The Crow Search algorithm and FA are integrated to
expense, and CPU idle time were considered optimization enhance global search capability [203]. A hybrid Firefly-
criteria for mapping the dependent tasks. The traditional Genetic combination is propounded for scheduling tasks in
genetic algorithm is supplemented with CSO and DBCSO [204]. An intelligent meta-heuristic algorithm based on the
to initialize the population [192]. combination of ICA and FA has been presented in [205] to
show dramatic improvements in makespan, CPU time, load
4.1.2.6 Whale optimization algorithm An innovative balancing, stability, and planning speed. Another hybrid
method for handling optimization issues is the Whale method using Firefly and SA algorithms has been proposed
Optimization Algorithm (WOA). Three operators are used in [206]. The Cat Swarm Optimization and the FA were
in this algorithm to replicate how humpback whales hunt combined into a hybrid multi-objective scheduling algo-
by searching for prey, circling prey, and using bubble nets. rithm [207]. An original modified Firefly Algorithm (mFA)
The bubble-net feeding method is the name of this foraging is used to construct and successfully optimize the opera-
technique [193]. By optimizing the allocation of tasks to tional cost minimization problem for DGDCs [208].
resources, the WOA algorithm can reduce the makespan

123
 Cluster Computing

4.1.2.8 Crow search algorithm A novel kind of swarm and manage resources [225] efficiently. The Multi-objec-
intelligence optimization algorithm known as the ‘‘Crow tive Cuckoo Search Optimization (MOCSO) algorithm is
Search Algorithm’’ was developed by imitating the intel- suggested to resolve multi-objective resource scheduling
ligent behavior of crows in hiding and finding food [209]. issues in an IaaS cloud computing context [226]. A com-
The Crow Search method has been applied to optimization bination of Cuckoo Search and oppositional-based learning
problems. The Crow Search is proposed in [210] for task (OBL) has created a new hybrid algorithm called the
scheduling in the cloud. Enhanced Crow Search Algorithm Oppositional Cuckoo Search Algorithm (OCSA) [227].
(ECSA) is proposed in [211] to improve the random Madni et al. developed the Hybrid Gradient Descent
selection of tasks. A technique called the Crow-Penguin Cuckoo Search (HGDCS) algorithm based on the Gradient
Optimizer for Multi-objective Task Scheduling Strategy in Descent (GD) approach and Cuckoo Search algorithm to
Cloud Computing (CPO-MTS) is suggested in [212]. The optimize and address issues with resource scheduling in
suggested algorithm quickly determines how to best use the IaaS cloud computing [228]. The CHSA algorithm, a mix
given tasks and cloud resources to complete them. In a of the Cuckoo Search and Harmony Search (HS) algo-
multi-objective task scheduling environment, Singh et al. rithms, is used to optimize the scheduling process [229]. A
propose the Crow Search-based Load Balancing Algorithm group technology-based model and Cuckoo Search algo-
(CSLBA), which focuses on allocating the best resources rithm are proposed for resource allocation [230].
for the task to be implemented while considering different A Hybridized Optimization algorithm that is the combi-
factors like the Average Makespan Time (AMT), Average nation of the ’Shuffled Frog Leaping Algorithm’ (SFLA)
Waiting Time (AWT), and Average Data Center Process- and ’Cuckoo Search’ (CS) Algorithm for resource alloca-
ing Time (ADCPT) [213]. The task resource mapping tion is proposed in [231].
problem is addressed using a Crow Search-based load
balancing method for enhanced optimization [214]. To fix 4.1.2.10 Grey wolf search optimization algorithm A
the issue with the resource allocation model, a new opti- meta-heuristic optimization algorithm called grey wolf
mization technique known as Grey Wolf Optimization and optimization (GWO) was developed after studying the
Crow Search Algorithm (GWO-CSA) is created [215]. The social interactions of grey wolves [232]. The GWO algo-
Crow Search algorithm and the Sparrow Search Algorithm rithm is modeled on how grey wolves hunt, which involves
(SSA) are combined to minimize energy in the cloud working together as a pack to catch prey. Natesan et al.
computing environment [216]. Mangalampalli et al. pro- propose simulating the performance cost grey wolf opti-
posed a multi-objective task scheduling method using the mization (PCGWO) algorithm to optimize allocating
Crow Search Algorithm to schedule tasks to the appropri- resources and tasks in cloud computing [233]. The publi-
ate virtual machines while considering the cost per energy cation [234] offers the modified fractional grey wolf opti-
unit in data centers [217]. mizer for multi-objective task scheduling (MFGMTS), a
multi-objective optimization technique. Grey wolf opti-
4.1.2.9 Cuckoo search algorithm Cuckoo Search is one of mizer is also proposed in [235]. A hybrid algorithm
the most recent algorithms to draw inspiration from nature. Genetic Gray Wolf optimization algorithm (GGWO), is
Cuckoo Search is based on some cuckoo species’ brood proposed by combining gray wolf optimizer (GWO) and
parasitism [218]. Additionally, the so-called Lévy flights genetic algorithm [236]. In the study [237], a mean GWO
improve this technique. The Cuckoo Search algorithm is algorithm has been developed to enhance the system per-
proposed in [219, 220] to optimize task scheduling in cloud formance of task scheduling in the heterogeneous cloud
computing. A combination of two optimization algorithms, environment. A multi-objective GWO technique has been
Cuckoo Search and PSO (CPSO), has been proposed in developed in [238] for task scheduling to achieve the best
[221] paper to reduce the makespan, cost, and deadline possible use of cloud resources while minimizing the data
violation rate. The Cuckoo Crow Search Algorithm center’s energy consumption and the scheduler’s overall
(CCSA) is an effective hybridized scheduling method makespan for the given list of tasks. Using the hill-
developed in [222] to find an appropriate VM for task climbing approach and chaos theory, Mohammadzadeh
scheduling. The cuckoo search-based task scheduling et al. [239] devised IGWO, an enhanced version of the
method suggested in [223] assists in efficiently allocating GWO algorithm that speeds up convergence and avoids
tasks among the available virtual machines and maintains a getting caught in the local optimum. Particle Swarm
low overall response time (QoS). For better resource Optimization and Grey Wolf Optimization, two well-
management in the Smart Grid, a load-balancing strategy known meta-heuristic algorithms, have been combined to
based on the Cuckoo Search is suggested in [224]. form the PSO-GWO algorithm, which has been proposed
A Standard Deviation-based Modified Cuckoo Optimiza- in [240]. The experiment’s findings indicate that, compared
tion Algorithm (SDMCOA) is described to schedule tasks to the traditional Particle Swarm Optimization and Grey

123
Cluster Computing

Wolf Optimization techniques, the PSO-GWO methodol- are Henry Gas Solubility Optimization [251], Simulated
ogy reduces the average total execution cost and time. Annealing (SA) [252], Gravitational Local Search (GLSA)
[253], Big-Bang Big-Crunch (BBBC) [254], Gravitational
4.1.2.11 Glowworm swarm optimization The glowworm Search Algorithm (GSA) [255], Charged System Search
swarm optimization (GSO) method simulates the move- (CSS) [256], Central Force Optimization (CFO) [257],
ment of the glowworms in a swarm depending on the Artificial Chemical Reaction Optimization Algorithm
distance between them and on a luminous substance called (ACROA) [258], Black Hole (BH) [259], Ray Optimiza-
luciferin [241]. It is a relatively recent swarm intelligence tion (RO) [260]. In this section, some physics-based nature-
system. The article [242] proposes a hybrid glowworm inspired algorithms that are used in task scheduling of
swarm optimization (HGSO) based on GSO to achieve cloud computing are briefly summarized.
more effective scheduling with affordable costs. The sug-
gested HGSO speeds up convergence and makes it easier to 4.1.3.1 Henry gas solubility optimization Henry’s law is a
escape from local optima by reducing unnecessary com- fundamental gas law that describes how much of a given
putation and dependence on GSO initialization. GSO is gas dissolves in a specific kind and amount of liquid at a
used in paper [243] to address the task scheduling issue in specific temperature. The Henry Gas Solubility Optimiza-
cloud computing in order to reduce the overall cost of job tion (HGSO) algorithm mimics the huddling behavior of
execution while maintaining on-time task completion. gas to balance exploitation and exploration in the search
space and prevent local optima. A modified Henry gas
4.1.2.12 Symbiotic organism search optimization algo- solubility optimization for the best task scheduling is pro-
rithm The symbiotic organism search (SOS) optimiza- vided in the paper [261] and is based on the WOA and
tion technique is a nature-inspired optimization technique Complete Opposition-Based Learning (COBL). Henry Gas
that can be used for cloud computing task schedules. The Solubility Whale Cloud (HGSWC) is the name of the
algorithm is founded on the idea that organisms can coexist proposed technique. A set of 36 optimization benchmark
harmoniously and use one another’s advantages to survive. functions is used to validate HGSWC, compared to tradi-
The discrete symbiotic organism search (DSOS) technique tional HGSO and WOA.
is presented in the publication [244] for optimal task
scheduling on cloud resources. The discrete symbiotic 4.1.3.2 Simulated annealing Simulated Annealing (SA)
organism search (DSOS) method has improved, but is a technique for resolving bound- and unconstrained
because the makespan and response time parameters are so optimization issues. The technique simulates the physical
significant, it still gets stuck in local optima. As a result, a procedure of raising a material’s temperature and gradually
quicker convergent technique for enhanced Discrete Sym- decreasing it to reduce flaws while conserving system
biotic Organism Search (eDSOS) is suggested in [245] energy. A combination of Firefly and SA has been pre-
when the search space is more extensive or more prominent sented in [206].
due to diversification. The chaotic symbiotic organisms
search (CMSOS) technique is developed to resolve the 4.1.4 Hybrid algorithm
multi-objective large-scale task scheduling optimization
problem in the IaaS cloud computing environment [246]. In hybrid scheduling algorithms, two or more scheduling
The Adaptive Benefit Factors-based Symbiotic Organisms algorithms are merged to address the task scheduling issue
Search (ABFSOS) method is presented to balance local and in a cloud context. The fundamental concept behind hybrid
global search techniques for a faster convergence speed algorithms is to combine the benefits of various methods
[247]. An energy–aware Discrete Symbiotic Organism into a single algorithm to improve performance in terms of
Search (E-DSOS) Optimization algorithm has been pro- computation time, result in quality, or both. [262] discusses
posed in [248] for task scheduling in a cloud environment. combining ACO and PSO techniques to improve resource
A modified Symbiotic Organisms Search Algorithm scheduling. The performance and quality of the solution are
(G_SOS) is suggested to reduce task execution time optimized using a similar hybrid technique by the authors
(makespan), cost, reaction time, and degree of imbalance in [263] employing ACO and Intelligent Water Drop
and speed up convergence for an ideal solution in an IaaS algorithm. ACO with Particle Swarm (ACOPS) [264] is
cloud [249]. presented to schedule VMs more efficiently. In this
method, the burden of user requests is dynamically fore-
4.1.3 Physics-based algorithm casted and mapped onto the available VMs. In [265],
authors introduced an algorithm that optimizes work
Methods based on physics mimic the laws of physics that scheduling in cloud environments using fundamental
govern the cosmos [250]. The most widely used algorithms notions from ACO and ABC. A hybrid Gravitational

123
 Cluster Computing

Emulation Local Search approach and PSO is used in [152] 4.3 Nature of task
to enhance the results. In [148], the hill climbing local
search heuristic is integrated with PSO, and in [266], fuzzy There are two scheduling techniques: independent and
logic and GSO are described. dependent scheduling (workflow scheduling). When
dependent scheduling is used, a workflow connects the
4.2 Nature of scheduling problem tasks to one another. The tasks are autonomous in inde-
pendent scheduling because they are not dependent on one
Developing an optimization model that satisfies the another. Several authors used both scheduling in their
objectives by locating the best optimal solution is neces- proposed system. Table 3 depicts the categorization of
sary because there is always an agreement between opti- techniques reviewed based on the nature of task.
mization objectives. Therefore, two types of scheduling
objectives are considered for nature-inspired task 4.4 Primary objectives of scheduling
scheduling. Table 2 represents the categorization of tech-
niques reviewed based on the nature of the scheduling Based on specific scheduling criteria, the scheduling pro-
problem. cess distributes the tasks inside the workflow onto the
appropriate resources. The scheduling criteria, such as
4.2.1 Single objective execution time, cost, reliability, and load balancing influ-
ence the success of the scheduling challenge. Tables 4, 5, 6,
It is feasible to evaluate the optimality of a specific solution and 7 illustrate the categorization of techniques based on
in contrast to another one already existing in a single primary objectives of scheduling using the evolutionary
objective optimization. For predetermined objectives, a algorithm, swarm intelligence-based algorithm, physics-
single best solution is chosen. Regarding task scheduling in base algorithm, and hybrid algorithm, respectively.
cloud computing, most approaches only consider the CPU
and memory requirements. 4.4.1 Makespan

4.2.2 Multi-objective Makespan is described as the overall time required to

execute the whole workflow by considering the time when
It is possible to characterize task scheduling in a distributed the tasks finished their execution and the time when it has
heterogeneous computing system as a non-linear, multi- been submitted [290]. In the literature, most of the
objective, and NP-hard optimization problem that aims to scheduling algorithms have focused on optimizing make-
maximize cloud resource consumption while meeting QoS span [79, 291]. However, minimizing the total execution
standards. It is impossible to directly compare one solu- time reduces the execution cost while mapping the tasks to
tion’s optimality to another already existing in multi-ob- the resources.
jective optimization. Multi-objective scheduling often uses
a Pareto dominance relation technique to replace a single 4.4.2 Security
optimal solution with various possibilities and provide
numerous, varied trade-offs between the objectives. Due to the heterogeneous and scattered nature of cloud
computing resources, security is a significant concern.
Because of virtualization and multi-tenancy capabilities,
providing data security and privacy in a cloud environment
is more challenging than in traditional systems.

Table 2 Nature of scheduling problem 4.4.3 Reliability

References Nature-inspired algorithm
Failures during the execution of a workflow can occur for
Single objective [267] FA, CSA, and SA
various reasons, including resource unavailability, resource
Multi-objective [268] PSO failure, and network infrastructure. As a result, the
[269] PSO scheduling mechanism should consider resource failure and
[270] ACO ensure reliable executions even when there is concurrency
[271] PSO and failure. The likelihood that the tasks will be carried out
[226] CSA successfully and the workflow will be completed is known
as reliability. For an application to run smoothly, all

123
Cluster Computing

Table 3 Nature of task

Reference Algorithm

Independent [267] FA, CSA, and SA

[268] PSO
[269] PSO
[271] PSO
[226] CSA
[272] Hybrid (ACO and CSA)
[273] PSO
[274] CSO
[275] GA
[276] chaotic ACO and GA
[277] GA
[278] FA
[279] ABC and PSO
Workflow [280] GA
[281] ACO
[282] ACO, PSO, and GA
[283] Hybrid (SA with CSO)
[284] PSO
[285] PSO
[286] GA
Independent and workflow scheduling [270] ACO
[287] GA
[288] IE-ABC
[289] PSO and CSO

resources must be reliable. It is possible to calculate the balancing over the resource enhances resource consump-
failure rate; thus, the mapping should be carried out to tion and the efficiency of the scheduling process.
increase reliability and lower failure rates. Task-level, VM-
level, and workflow-level failures are the three levels of 4.4.6 Resource utilization
failure in a workflow application.
The service provider benefits from higher resource uti-
4.4.4 Cost lization to maximize profit by renting out scarce resources
to users to ensure full utilization.
The cost of an application is determined by two factors
depending on two fundamental cloud resources: the cost of 4.4.7 Rescheduling
computing and the cost of data transit and storage. By
supplying a lot of resources, the overall execution time can Because rescheduling necessitates re-evaluating the plan
be reduced, but execution costs, scheduling overheads, and and the cost of data transportation among the dependent
resource underutilization may all rise as a result. activities over the multiple machines, it is generally con-
sidered an overhead to the scheduling process [292]. A
4.4.5 Load balancing heavy load on the server can need rescheduling.
Rescheduling the jobs is also necessary in the event of
In cloud computing settings, virtual computers predomi- failures such as VM shutdowns or system faults [293].
nate as the processing components. There may be instances Only some tasks are chosen for rescheduling because it
during scheduling where multiple tasks are allocated to lengthens execution time overall and causes performance
virtual machines (VMs) for simultaneous execution. The to suffer.
loads on the VMs become imbalanced as a result. The
scheduler should be able to spread the burden to the
available ones to prevent overloading resources. Load

123
 Cluster Computing

Table 4 Primary objectives of scheduling for the evolutionary algorithm

Algorithm Reference Reliability Makespan Cost Security Load Balance Energy Efficient Rescheduling Resource Utilization

GA [297] Yes Yes Yes – – – – –

[79] – Yes Yes Yes – – – –
[298] – Yes – – – – – –
[75] – Yes – – Yes – – –
[76] – Yes - Yes – – – –
[294] – – – – – Yes – Yes
[68] – Yes – – – – – Yes
[69] – – - – Yes – – –
[70] – – – – – – – Yes
[71] – Yes – – – – – -
[72] – – – – – – – Yes
MA [88] Yes Yes – – – – –
[90] Yes Yes – – – – –
[91] – Yes – – – – – –
ICA [99] Yes – – – – – – –
[103] – Yes – – – – – –
[104] Yes – – – – Yes – –
LOA [299] – Yes Yes – Yes – – Yes
SFO [107] – Yes – – – Yes –
[108] – – – – – – – Yes

4.4.8 Energy efficiency 4.5.1 Budget

The amount of CPU and resources used directly influences Budget is a limitation the user imposes on using the cloud
how much energy a task uses. When CPUs are not service provider’s resources. Scheduling decisions are
appropriately utilized, idle power is not utilized effectively, made utilizing the budget constraint to minimize the
resulting in significant energy consumption. Due to the workflow’s overall execution time and guarantee that it is
high resource demand, it might occasionally consume completed within the budget.
much energy, reducing performance [294]. Scheduling
decisions are crucial, to limit the energy consumption of 4.5.2 Deadline
the allocated resource. They help determine the best order
in which tasks should be completed. An energy-efficient Applications that depend on timing must finish running in a
storage service is one of the strategies for reducing power specific amount of time. These applications are made to
usage addressed in [295]. This service may create a pre- give results before the deadline using deadline-constrained
dictive model to forecast how users will use the files and scheduling. When scheduling jobs, deadline-constrained
data stored there. A few scheduling algorithms might even scheduling must also consider the associated costs. In time-
be created to lower energy usage [296]. sensitive applications, robust scheduling with deadlines is
essential since it increases the dependability of the
4.5 Scheduling constraints program.

The possibility of the SLA being negatively impacted if 4.5.3 Fault tolerant
many applications cannot meet the deadline, priority,
budget, and fault tolerance limits are essential concerns in A cost-effective fault tolerant (CEFT) scheduling strategy
cloud scheduling. The suggested mechanisms in this that should adhere to a predetermined deadline in cloud
respect are detailed in the subsections that follow. Table 8 systems was discussed in the paper [257]. This method of
illustrates the categorization of techniques based on handling jobs, known as the primary/backup (P/B) strategy,
scheduling constraints. contains two duplicate copies of each task and offers

123
Cluster Computing

Table 5 Primary objectives of scheduling for swarm intelligence-based algorithm

Reference Reliability Makespan Cost Security Load Energy Rescheduling Resource
Balance Efficient Utilization

ACO [300] – Yes – – Yes – – –

[301] – Yes – – – – – –
[133] – Yes Yes – – – – –
[134] – Yes Yes – – – – –
[138] – Yes – – – – – –
PSO [302] – Yes – Yes – – – –
[295] – Yes Yes Yes Yes – – –
[146] – Yes Yes – – – – –
[147] – – Yes – – – – –
ABC [168] – Yes – – – – – –
[169] – Yes – – – – – –
[170] – – – – Yes Yes – Yes
[171] – – – – Yes – – –
[172] – – – – Yes – – Yes
BA [181] – Yes Yes – – – – –
[182] – Yes - – – – – –
[184] – Yes Yes – – – – –
CSO [191] – – Yes – Yes – – –
[192] – – Yes – – – – –
WOA [198] – Yes Yes – – – – –
[196] – Yes Yes – – – – –
[199] – Yes Yes – – Yes – Yes
[195] – – Yes – – Yes – –
[194] – Yes Yes – – – – –
FA [201] – Yes Yes – – – – –
[207] – Yes Yes – Yes – – –
[204] – Yes – – – – – –
Crow Search [217] – Yes – – – Yes –
[212] – Yes Yes – Yes – – Yes
[214] – – Yes – – Yes – –
[210] – Yes – – – – – –
[213] – – – – – – – Yes
Cuckoo [223] – – – – Yes – – –
Search [224] – Yes – – – – – –
[225] – Yes Yes – Yes – – –
[226] – Yes Yes – – – – –
[227] – Yes – – – – – –
[228] – Yes Yes – – – – –
[229] – Yes – – Yes – – –
GWO [236] – Yes Yes – Yes Yes – –
[241] – Yes Yes – – – – –
[240] – Yes Yes – – – – –
[239] – Yes Yes – – Yes – –
GSO [242] – Yes Yes – – – – –
SOS [244] – Yes – – – – – –
[245] – Yes – – – – – –
[246] – – – – – Yes – –

123
 Cluster Computing

Table 6 Primary objectives of scheduling for physics-based algorithm

Reference Reliability Makespan Cost Security Load Balance Energy Efficient Rescheduling Resource Utilization

HGSA [261] – Yes Yes – – – – –

SA [206] – Yes – – – – – –

Table 7 Primary objectives of scheduling for hybrid algorithm

Reliability Makespan Cost Security Load balance Energy efficient Rescheduling Resource utilization

ABC and PSO [279] – Yes – – – Yes – –

ACO with CRO [281] – Yes Yes – – – – –
ACO and CSO [282] – Yes – – – – –
ACO and GA [272] – Yes – – – – –
ACO with GSA [277] – Yes – Yes – - – Yes
CSA with HGSA [283] – Yes Yes – – Yes – –
GA with ANN [287] – Yes – – – Yes – –
GA with fuzzy [303] – Yes – – – – – –

Table 8 Scheduling constraints Table 9 Task resource mapping scheme

References Nature-inspired algorithm Reference Nature-inspired algorithm

Deadline [304] PSO Static [171] ABC

[282] ACO Dynamic [309] ACO and PSO
[289] PSO and CSO [312] GA
Priority [305] PSO [313] PSO
[306] BFO [314] GA
Budget [307] PSO AI [310] PSO
Fault tolerance [308] PSO [315] PSO
Prediction [311] ACO
[285] GA
permanent or temporary fault tolerance in the event of
hardware failure. The tasks in this strategy are independent 4.6 Task-resource mapping scheme
and do not follow a hierarchy. The iterative method is used
to optimize the suggested resource allocation technique To effectively utilize the available resources based on the
more successfully. The PSO method chooses VM for the cloud environment and the submitted workload, static,
next task in each iteration. dynamic, AI-based, and prediction-based mapping of cloud
resources to incoming tasks are carried out. Table 9 illus-
4.5.4 Priority trates the categorization of techniques based on the task
resource mapping scheme.
Verma and Kaushal suggested a Bi-Criteria priority-based
PSO (BPSO), lowering the makespan and execution costs 4.6.1 Static
while scheduling cloud workflow activities [305]. This
PSO would take into consideration deadlines and financial Static scheduling involves prior knowledge of the tasks to
restrictions. Each workflow task is prioritized at the bottom decide on a schedule before a task begins to execute. By
level specified by the HEFT algorithm so that the PSO can enhancing load balancing among VMs and balancing the
carry out the tasks according to these priorities. priority of the activities on those VMs, the paper [171]
suggested a resource provisioning technique inspired by the
ABC algorithm’s behavior to boost resource utilization,
increase system throughput, and decrease queuing time.

123
Cluster Computing

4.6.2 Dynamic examining novel scheduling algorithms and judging their

efficiency in various cloud environments. The most well-
Dynamic scheduling may occur while a task is being known tool for task scheduling is the CloudSim simulation
executed and doesn’t need to be aware of every task toolkit. Its existing programmatic classes can be expanded
property. When maximizing resource use is more critical by the algorithm needed to assess a variety of QoS
than reducing execution time, this helps manage changing parameters, including makespan, financial cost, computa-
requirements of cloud users [219]. All meta-heuristic tional cost, reliability, availability, scalability, energy
scheduling techniques are, in fact, dynamic [220]. How- consumption, security, and throughput, as well as includi-
ever, some research is discussed in this subsection based on ble constraints, such as deadline, priority, budget, and fault
the dynamic cloud environment and the dynamic schedul- tolerance. iCloud, GridSim, CloudSim, CloudAnalyst,
ing system specified in the primary keyword of the selected NetworkCloudSim, Work flowSim, GreenCloud, and more
articles. Islam and Habiba have proposed dynamic well-known simulation tools are available on the cloud.
scheduling methods based on ACO and Variable Neigh- Table 10 illustrates the categorization of techniques based
borhood PSO (VNPSO) [309]. on testing tools.

4.6.3 Artificial intelligence (AI)-based

5 Analysis and discussions
The creation of an intelligent method that works and
responds, like humans, to schedule and assign resources This section comprehensively summarizes and examines
with various aspects, such as intelligent and autonomous the nature-inspired meta-heuristics techniques for task
systems, nature-inspired intelligent systems, operational scheduling in cloud computing in terms of the scheduling
research systems, agent-based systems, neural networks, algorithm, type of tasks, the primary objective of
machine learning, and expert systems, is supported by the scheduling, task-resource mapping scheme, scheduling
highly technical and specialized methodology known as constraint, and testing environment.
AI-based scheduling [226]. Greater accuracy and precision
are ensured for resource allocation and scheduling in the 5.1 Scheduling algorithm
cloud framework with AI, and failure and error rates are
nearly nonexistent. ML algorithms have been used in cloud Figure 3 shows how various task scheduling methods for
computing to forecast the status of the resources based on clouds inspired by nature can be divided into swarm,
their anticipated future load and security. Incoming evolutionary, physics, and hybrid approaches, along with
requests were mapped to resources using an ANN model by the proportions of each most commonly used approach.
paper [310]; to complete the task more quickly. The majority of the algorithms used in the literature are
swarm-based optimization methods. The most active
4.6.4 Prediction-based algorithm among them is PSO, as seen in Fig. 4. Some-
times, those algorithms are used with additional meta-
Prediction-based scheduling relates to how various tech- heuristic or heuristic techniques. Because a hybrid version
niques and measurements behave when allocating resour- of the system can further improve overall performance, the
ces. When it comes to efficient task scheduling and search strategy and convergence speed of meta-heuristic
optimum resource allocation in the cloud environment, it techniques vary. Therefore, the hybrid algorithm achieves
can be essential to estimate the critical resource require- the second rank in the list. Most researchers used the GA in
ments and users’ demand for the future using automatic evolutionary approaches, as seen in Fig. 5.
resource allocation or resource reservation approaches
[231, 232]. Paper [311] introduced a Prediction-based ACO 5.2 Scheduling objective
classification algorithm (PACO), which operates based on
task prioritization and considers various QoS criteria to Multi-objective techniques have more scheduling strategies
minimize the workflow’s overall execution time and than single-objective, as shown in Fig. 6. Consequently, it
guarantee that it is completed within the budget. encourages the ongoing incorporation of multi-objective
strategies for more dependable task scheduling in the cloud
4.7 Testing tools and their comparison environment.

Testing new strategies in an authentic setting is almost

impossible because some trials could harm the end-user
QoS. There are numerous well-known simulation tools for

123
 Cluster Computing

Table 10 Testing environment

Reference Nature-inspired algorithm

GCC compiler [267] FA, CSA, and SA

CloudSim [268] PSO
[269] PSO and GA
[270] PSO
[226] CSA
[273] PSO
[274] PSO
Real environment [272] ACO and CSA
[280] GA
CloudSim and real environment [270] ACO
[285] PSO
Matlab [288] PSO
[276] chaotic ACO and GA
[277] GA
CloudSim with MATLAB [287] GA
GridSim [312] GA
Java [282] ACO
[310] PSO
[307] PSO

Evolutionary Swarm Physics Hybrid PSO ACO ABC Crow search Cuckoo search
45
40
35
Number of schemes

30
25
20
15
10
5
0
PSO ACO ABC Crow search Cuckoo search

Fig. 3 Usage measurement of nature-inspired algorithm Fig. 4 Usage measurement of swarm algorithm

5.3 Type of task element is cost. Only a few studies, as shown in Fig. 8,
have utilized reliability into consideration while scheduling
The most used type of task scheduling is independent tasks. Reliable scheduling can lessen the impact of resource
rather than workflow scheduling. Some literature reviews breakdowns. Making scheduling decisions using the
also use the combination of independent and workflow application’s failure probability as a minimum considera-
scheduling. The usage measurement of the type of task tion is recommended. The service providers must consider
scheduling for nature-inspired algorithms is illustrated in resource consumption. Proper resource usage will be
Fig. 7. achievable if the submitted applications have the necessary
resources. However, there are connections between the use
5.4 Primary objectives of scheduling of resources and energy consumption. The fundamental
concept behind enhancing resource usage is to combine the
The algorithms are examined in light of the different load on the virtual machines (VMs) such that the spare
scheduling objectives in Fig. 8. The many QoS parameters VMs can be turned off or repurposed for new application
that different scheduling algorithms take into consideration demands. In this situation, predicting future resource
are shown in Fig. 8. The makespan is the most often demand can help cloud service providers turn a profit.
employed scheduling objective. The second most crucial

123
Cluster Computing

GA MA ICA LOA 12
35
10
30

Number of schemes
8
Number of schemes

25

20 6

15 4
10
2
5
0
0 Makespan Cost Load Energy Resource Reliability Security
GA MA ICA LOA balancing efficiency utilization

Fig. 5 Usage measurement of evolutionary algorithm Fig. 8 Frequency of scheduling objectives

Single objective Multi objective Static Dynamic AI Prediction

Fig. 6 Usage measurement of scheduling objective algorithm Fig. 9 Usage measurements of task resource management

Independent Workflow Hybrid CloudSim Java GCC compiler CloudAnalyst Real environment

Fig. 7 Usage measurements of types of task Fig. 10 Usage measurements of the testing environment

Reducing VM migrations might be made more accessible 5.6 Task resource mapping scheme
with the estimation.
Dynamic scheduling has the most excellent use in nature-
5.5 Scheduling constraints inspired optimization problems. AI and prediction-based
scheduling are also more widely used than static schedul-
Deadline is the constraint most emphasized by nature-in- ing, as depicted in Fig. 9.
spired techniques. Fault tolerance is also a widely adopted
constraint. Most studies also concentrated on budget and 5.7 Testing environment
priority at the time of scheduling.
CloudSim is the most popular and widely used testing tool
in implementing nature-inspired task scheduling

123
 Cluster Computing

algorithms, as depicted in Fig. 10. A few studies also used desired QoS level. Developing novel practical solutions in
GridSim, java, Matlab, etc. in some works. this field still requires additional research effort. There
must be a minimum amount of contact between the com-
5.8 Discussion puting environment and the cloud consumer to fulfill the
QoS standards specified by users while maintaining the
In this study, a novel taxonomy has been used to com- SLA. Performance degradation could therefore be pre-
prehensively and meticulously categorize different popular vented through research into an efficient autonomic
nature-inspired scheduling approaches in the cloud in terms infrastructure-based technique that, in advance, detects
of the scheduling algorithm, the nature of the scheduling SLA violations.
problem, the type of task, the main scheduling goal, the Increasing energy efficiency in cloud computing is one
task-resource mapping scheme, the scheduling constraint, of the main issues. According to estimates, 53% of all
and the testing environment. operational expenses go into cooling and powering data
Swarm-based optimization techniques are used in most centers. As a result, IaaS providers have been given the
of the scheduling algorithms used in the literature. The urgent responsibility of reducing energy use. The goal of
most popular swarm-based technique for scheduling issues data center design should not only be to save energy costs;
in clouds is Particle Swarm Optimization. The majority of it also needs to comply with environmental regulations and
researchers use Genetic Algorithms in evolutionary-based legal requirements. Energy-aware server consolidation and
techniques as well. These algorithms are occasionally energy-efficient task scheduling can be used to lower
integrated with different heuristics or meta-heuristic power usage by turning off idle systems. Since cloud ser-
methods. Most of the studies are multi-objective and vice providers today seek to offer their services to end
independent. In maximal meta-heuristic algorithms, customers with high performance, high quality, and mini-
makespan is employed as the scheduling objective. As mal processing time while making maximum profit, relia-
scheduling objectives, cost and energy efficiency are also bility is one of the most demanding cloud computing
given preference. Security and reliability parameters concerns. The scheduling strategy should be used to safe-
receive less focus. The deadline is the constraint that nat- guard and protect the private and sensitive data contained
ure-inspired techniques highlight most. Additionally, fault in the submitted applications.
tolerance is a widely used restriction. Dynamic scheduling As can be observed from the numerous state-of-the-art
achieves higher popularity than static, AI, and prediction- scheduling methods chosen for this study, not all problems
based approaches. The most widely used task scheduling (challenges) can be solved by a single algorithm. For
tool is the CloudSim simulation toolkit, whose existing instance, while an algorithm considers different factors,
programmatic classes can be expanded in accordance with such as resource utilization, availability, response time,
the algorithm requirements to evaluate a variety of QoS scalability, etc., it may entirely neglect the energy, cost,
parameters, including makespan, monetary cost, computa- time, and quality of service (QoS) parameters that are the
tional cost, reliability, availability, scalability, energy emphasis of the other algorithm. Hybrid algorithms can be
consumption, security, and throughput. more inventively modified to individually or collectively
maximize a variety of scheduling goals, such as energy
optimization, load balancing, scalable VM migration, etc.
6 Future research issues of nature-
optimization task scheduling algorithms
7 Conclusion
Although nature-inspired algorithms have been used in
many applications successfully, there is still plenty of space Many scientific applications can now migrate to the cloud
for analysis and discussion regarding many current prob- because of the adoption of the new distributed computing
lems and topics. Several areas need to be addressed in this paradigm and cloud computing infrastructure. With the
field. Cloud task scheduling presents a variety of difficul- advantages of cloud computing, including virtualization
ties, including heterogeneity, uncertainty, and resource and shared resource pools, it is possible to manage and run
dispersion, which conventional resource management large-scale workflow applications without maintaining
techniques need to address. Therefore, to increase the physical computing infrastructure. The use of numerous
dependability of cloud applications and services, a lot of resources accessible via the cloud needs to be optimized.
attention and significance should be given to these cloud Nature-inspired scheduling algorithms give better opti-
qualities. The workload should occupy the fewest resources mization results than traditional and heuristic. Over the
that will be effectively employed to achieve the shortest past few years, nature-inspired optimization has developed
job duration (maximize system throughput) and maintain a rapidly, establishing a significant trend in cloud task

123
Cluster Computing

scheduling. Several existing studies have employed nature- their primary QoS parameters, identify the best task-re-
inspired optimization algorithms to solve scheduling source mapping scheme, and establish the scheduling
problems. However, their studies do not concentrate on all constraints that are most suitable for the challenge, without
of the parameters required to analyze the importance of violating the SLA.
nature-inspired optimization algorithms in task scheduling.
Most studies only considered a small number of parameters
(such as state-of-the-art, QoS parameters, etc.). Still, they Author contribution FSP: writing original draft, literature surveys,
writing—review and editing; MdHG: draft manuscript preparation,
need to simultaneously assess taxonomy, graphical repre- writing—review, and editing; KMAU: study conception, supervision,
sentation, and research difficulties for a deeper under- and investigation on challenges.
standing of task scheduling techniques based on nature-
inspired optimization. To the best of our knowledge, a Funding The authors declare that no funds, grants, or other support
were received during the preparation of this manuscript.
thorough, systematic, taxonomic assessment of nature-in-
spired optimization scheduling approaches in the cloud is Data Availability Enquiries about data availability should be directed
required to keep up with the ever-increasing growth of to the authors.
nature-inspired algorithms. Therefore, a comprehensive
study of several nature-inspired meta-heuristics-based
Declarations
strategies has been conducted in this paper. Conventional
and heuristic scheduling approaches were presented to Conflict of interest The authors have no conflict of interest to
distinguish them from nature-inspired optimization algo- disclose.
rithms. A novel taxonomy has been demonstrated to
extensively and methodically classify various popular
nature-inspired scheduling approaches in the cloud References
regarding the scheduling algorithm, the nature of the
1. Kaur, R., Laxmi, V.: Performance evaluation of task scheduling
scheduling problem, the type of task, the primary
algorithms in virtual cloud environment to minimize makespan.
scheduling goal, the task-resource mapping scheme, the Int. J. Inf. Technol. (2022). https://doi.org/10.1007/s41870-021-
scheduling constraint, and the testing environment. The 00753-4
results of each classification stage of taxonomy are ana- 2. Gawali, M.B., Shinde, S.K.: Task scheduling and resource
allocation in cloud computing using a heuristic approach.
lyzed and comprehensively examined to provide a roadmap
J. Cloud Comput. 7(1), 1–16 (2018)
for researchers working in the area of scheduling for 3. Singh, S., Chana, I.: A survey on resource scheduling in cloud
enhancing cloud service. computing: issues and challenges. J. Grid Comput. 14, 217–264
In most literature, researchers have employed PSO and (2016)
4. Mathew, T., Sekaran, K.C. and Jose, J., 2014, September. Study
GA algorithms to carry out most cloud computing tasks.
and analysis of various task scheduling algorithms in the cloud
The most active study areas are makespan, cost, and computing environment. In 2014 International Conference on
resource utilization which are concentrated by most stud- Advances in Computing, Communications and Informatics
ies. Single objective scheduling, reliability, rescheduling, (ICACCI) (pp. 658–664). IEEE.
5. Xu, L., Qiao, J., Lin, S., Zhang, W.: Dynamic task scheduling
budget, priority, AI-based, and prediction-based mapping
algorithm with deadline constraint in heterogeneous volunteer
schemes have attracted less attention from researchers; as a computing platforms. Future Internet 11(6), 121 (2019)
result, they must be urgently included in ongoing research. 6. Damodaran, P., Chang, P.Y.: Heuristics to minimize makespan
The solutions produced by many nature-inspired methods of parallel batch processing machines. Int. J. Adv. Manuf.
Technol. 37, 1005–1013 (2008)
that are already in use can be improved by considering the
7. Kim, S.I., Kim, J.K.: A method to construct task scheduling
hybrid approach. The advantages of existing nature-in- algorithms for heterogeneous multi-core systems. IEEE Access
spired algorithms can be combined in a hybrid manner to 7, 142640–142651 (2019)
address various issues brought on by workflow applications 8. Pinedo, M. and Hadavi, K., 1992. Scheduling: theory, algo-
rithms and systems development. In Operations Research Pro-
that optimize across several criteria. At the end of the
ceedings 1991: Papers of the 20th Annual Meeting/Vorträge der
discussion, a few simulation tools used in cloud computing 20. Jahrestagung (pp. 35–42). Springer, Berlin
are briefly addressed and contrasted for implementing and 9. Houssein, E.H., Gad, A.G., Wazery, Y.M., Suganthan, P.N.:
testing new algorithms. This study also presented some Task scheduling in cloud computing based on meta-heuristics:
review, taxonomy, open challenges, and future trends. Swarm
outstanding research issues and upcoming modern trends.
Evol. Comput. 62, 100841 (2021)
This study primarily endeavored to strongly encourage the 10 Singh, H., Tyagi, S., Kumar, P.: Scheduling in cloud computing
depth of the fundamental ideas of nature-inspired task environment using metaheuristic techniques: a survey. In: Shal,
scheduling techniques in the cloud computing area, which V. (ed.) Emerging technology in modelling and graphics: pro-
ceedings of IEM graph 2018, pp. 753–763. Springer Singapore,
should give investigators and users advice on how to
Singapore (2020)
identify the nature of their scheduling problem, pinpoint

123
 Cluster Computing

11. Liu, Y., Zhang, C., Li, B., Niu, J.: DeMS: A hybrid scheme of 28. Hatchuel, A., Saidi-Kabeche, D., Sardas, J.C.: Towards a new
task scheduling and load balancing in computing clusters. planning and scheduling approach for multistage production
J. Netw. Comput. Appl. 83, 213–220 (2017) systems. Int. J. Prod. Res. 35(3), 867–886 (1997)
12. Kumar, D.: Review on task scheduling in ubiquitous clouds. 29. Lawler, E.L., Lenstra, J.K. and Rinnooy Kan, A.H.G., 1982.
J. ISMAC 1(01), 72–80 (2019) Recent developments in deterministic sequencing and schedul-
13. Allahverdi, A., Ng, C.T., Cheng, T.E., Kovalyov, M.Y.: A ing: a survey. In Deterministic and Stochastic Scheduling:
survey of scheduling problems with setup times or costs. Eur. Proceedings of the NATO Advanced Study and Research Insti-
J. Oper. Res. 187(3), 985–1032 (2008) tute on Theoretical Approaches to Scheduling Problems held in
14. Remesh Babu, K.R. and Samuel, P., 2016. Enhanced bee colony Durham, England, July 6–17, 1981 (pp. 35–73). Springer
algorithm for efficient load balancing and scheduling in cloud. Netherlands.
In Innovations in Bio-Inspired Computing and Applications: 30. Madni, S.H.H., Abd Latiff, M.S., Abdullahi, M., Abdulhamid,
Proceedings of the 6th International Conference on Innovations S.I.M., Usman, M.J.: Performance comparison of heuristic
in Bio-Inspired Computing and Applications (IBICA 2015) held algorithms for task scheduling in IaaS cloud computing envi-
in Kochi, India during December 16–18, 2015 (pp. 67–78). ronment. PLoS ONE 12(5), e0176321 (2017)
Springer International Publishing. 31. Mazumder, A.M.R., Uddin, K.A., Arbe, N., Jahan, L. and
15. Taillard, E.: Some efficient heuristic methods for the flow shop Whaiduzzaman, M., 2019, June. Dynamic task scheduling
sequencing problem. Eur. J. Oper. Res. 47(1), 65–74 (1990) algorithms in cloud computing. In 2019 3rd International con-
16. Morton, T., Pentico, D.W.: Heuristic scheduling systems: with ference on Electronics, Communication and Aerospace Tech-
applications to production systems and project management. nology (ICECA) (pp. 1280–1286). IEEE.
John Wiley, Hoboken (1993) 32. Chowdhury, N., M Aslam Uddin, K., Afrin, S., Adhikary, A.,
17. Bissoli, D.C., Altoe, W.A., Mauri, G.R. and Amaral, A.R., 2018, Rabbi, F.: Performance evaluation of various scheduling algo-
August. A simulated annealing metaheuristic for the bi-objective rithm based on cloud computing system. Asian J. Res. Comput.
flexible job shop scheduling problem. In 2018 International Sci. 2(1), 1–6 (2018)
Conference on Research in Intelligent and Computing in Engi- 33. Balharith, T. and Alhaidari, F., 2019, May. Round robin
neering (RICE) (pp. 1–6). IEEE. scheduling algorithm in CPU and cloud computing: a review.
18. Gong, G., Chiong, R., Deng, Q., Gong, X.: A hybrid artificial In 2019 2nd International Conference on Computer Applica-
bee colony algorithm for flexible job shop scheduling with tions & Information Security (ICCAIS) (pp. 1–7). IEEE.
worker flexibility. Int. J. Prod. Res. 58(14), 4406–4420 (2020) 34. Zhao, H. and Sakellariou, R., 2003. An experimental investi-
19. Zarrouk, R., Bennour, I.E., Jemai, A.: A two-level particle gation into the rank function of the heterogeneous earliest finish
swarm optimization algorithm for the flexible job shop time scheduling algorithm. In Euro-Par 2003 Parallel Pro-
scheduling problem. Swarm Intell. 13, 145–168 (2019) cessing: 9th International Euro-Par Conference Klagenfurt,
20. Sörensen, K., Glover, F.: Metaheuristics. Encycl. Operations Austria, August 26-29, 2003 Proceedings 9 (pp. 189-194).
Res. Manag. Sci. 62, 960–970 (2013) Springer, Berlin
21. Garg, D. and Kumar, P., 2019. A survey on metaheuristic 35. Li, B., Niu, L., Huang, X., Wu, H. and Pei, Y., 2018, December.
approaches and its evaluation for load balancing in cloud Minimum completion time offloading algorithm for mobile edge
computing. In Advanced Informatics for Computing Research: computing. In 2018 IEEE 4th International Conference on
Second International Conference, ICAICR 2018, Shimla, India, Computer and Communications (ICCC) (pp. 1929–1933). IEEE.
July 14–15, 2018, Revised Selected Papers, Part I 2 (pp. 36. Krishnaveni, H., Sinthujanitaprakash, V.: Execution time based
585–599). Springer Singapore. sufferage algorithm for static task scheduling in cloud. In:
22. Kaur, N. and Chhabra, A., 2016, March. Analytical review of Advances in big data and cloud computing: Proceedings of
three latest nature inspired algorithms for scheduling in clouds. ICBDCC18, pp. 61–70. Springer Singapore, Singapore (2019)
In 2016 International Conference on Electrical, Electronics, 37. Chen, H., Wang, F., Helian, N. and Akanmu, G., 2013, Febru-
and Optimization Techniques (ICEEOT) (pp. 3296–3300). ary. User-priority guided Min-Min scheduling algorithm for load
IEEE. balancing in cloud computing. In 2013 national conference on
23. Garg, D. and Kumar, P., 2019. A survey on metaheuristic parallel computing technologies (PARCOMPTECH) (pp. 1–8).
approaches and its evaluation for load balancing in cloud IEEE.
computing. In Advanced Informatics for Computing Research: 38. George Amalarethinam, D.I. and Kavitha, S., 2019.
Second International Conference, ICAICR 2018, Shimla, India, Rescheduling enhanced Min-Min (REMM) algorithm for meta-
July 14–15, 2018, Revised Selected Papers, Part I 2 (pp. task scheduling in cloud computing. In International Confer-
585–599). Springer Singapore. ence on Intelligent Data Communication Technologies and
24. Kalra, M., Singh, S.: A review of metaheuristic scheduling Internet of Things (ICICI) 2018 (pp. 895–902). Springer Inter-
techniques in cloud computing. Egypt. Inf. J. 16(3), 275–295 national Publishing.
(2015) 39. Mao, Y., Chen, X. and Li, X., 2014. Max–min task scheduling
25. Kaur, N. and Chhabra, A., 2016, March. Analytical review of algorithm for load balance in cloud computing. In Proceedings
three latest nature inspired algorithms for scheduling in clouds. of International Conference on Computer Science and Infor-
In 2016 International Conference on Electrical, Electronics, and mation Technology: CSAIT 2013, September 21–23, 2013,
Optimization Techniques (ICEEOT) (pp. 3296–3300). IEEE. Kunming, China (pp. 457–465). Springer India.
26. Tsai, C.W., Rodrigues, J.J.: Metaheuristic scheduling for cloud: 40. Sandana Karuppan, A., Meena Kumari, S.A. and Sruthi, S.,
a survey. IEEE Syst. J. 8(1), 279–291 (2013) 2019. A priority-based max-min scheduling algorithm for cloud
27. Nandhakumar, C. and Ranjithprabhu, K., 2015, January. environment using fuzzy approach. In International Conference
Heuristic and meta-heuristic workflow scheduling algorithms in on Computer Networks and Communication Technologies:
multi-cloud environments—a survey. In 2015 International ICCNCT 2018 (pp. 819–828). Springer Singapore.
Conference on Advanced Computing and Communication Sys- 41. Zhou, X., Zhang, G., Sun, J., Zhou, J., Wei, T., Hu, S.: Mini-
tems (pp. 1–5). IEEE. mizing cost and makespan for workflow scheduling in cloud
using fuzzy dominance sort based HEFT. Futur. Gener. Comput.
Syst. 93, 278–289 (2019)

123
Cluster Computing

42. Tong, Z., Deng, X., Chen, H., Mei, J., Liu, H.: QL-HEFT: a September 3–7, 2012. Proceedings 12 (pp. 577–588). Springer
novel machine learning scheduling scheme base on cloud Berlin Heidelberg.
computing environment. Neural Comput. Appl. 32, 5553–5570 60. Yang, S., Yao, X.: Experimental study on population-based
(2020) incremental learning algorithms for dynamic optimization
43. Nazar, T., Javaid, N., Waheed, M., Fatima, A., Bano, H. and problems. Soft. Comput. 9, 815–834 (2005)
Ahmed, N., 2019. Modified shortest job first for load balancing 61. Gandomi, M., Kashani, A.R., Farhadi, A., Akhani, M., Gan-
in cloud-fog computing. In Advances on Broadband and Wire- domi, A.H.: Spectral acceleration prediction using genetic pro-
less Computing, Communication and Applications: Proceedings gramming based approaches. Appl. Soft Comput. 106, 107326
of the 13th International Conference on Broadband and Wire- (2021)
less Computing, Communication and Applications (BWCCA- 62. Hussain, I., Ullah, I., Ali, W., Muhammad, G., Ali, Z.:
2018) (pp. 63–76). Springer International Publishing. Exploiting lion optimization algorithm for sustainable energy
44. Alworafi, M.A., Dhari, A., Al-Hashmi, A.A. and Darem, A.B., management system in industrial applications. Sustain. Energy
2016, December. An improved SJF scheduling algorithm in Technol. Assess. 52, 102237 (2022)
cloud computing environment. In 2016 International Confer- 63. Hosseini, S., Al Khaled, A.: A survey on the imperialist com-
ence on Electrical, Electronics, Communication, Computer and petitive algorithm metaheuristic: implementation in engineering
Optimization Techniques (ICEECCOT) (pp. 208–212). IEEE. domain and directions for future research. Appl. Soft Comput.
45. Seth, S., Singh, N.: Dynamic heterogeneous shortest job first 24, 1078–1094 (2014)
(DHSJF): a task scheduling approach for heterogeneous cloud 64. Gomes, G.F., da Cunha, S.S., Ancelotti, A.C.: A sunflower opti-
computing systems. Int. J. Inf. Technol. 11(4), 653–657 (2019) mization (SFO) algorithm applied to damage identification on
46. Devi, D.C., Uthariaraj, V.R.: Load balancing in cloud comput- laminated composite plates. Eng. Comput. 35, 619–626 (2019)
ing environment using improved weighted round robin algo- 65. Guo, W., Chen, M., Wang, L., Mao, Y., Wu, Q.: A survey of
rithm for nonpreemptive dependent tasks. Sci. World J. (2016). biogeography-based optimization. Neural Comput. Appl. 28,
https://doi.org/10.1155/2016/3896065 1909–1926 (2017)
47. Venkataraman, N.: Threshold based multi-objective memetic 66. Aguilar-Rivera, R., Valenzuela-Rendón, M., Rodrı́guez-Ortiz,
optimized round robin scheduling for resource efficient load J.J.: Genetic algorithms and Darwinian approaches in financial
balancing in cloud. Mobile Netw. Appl. 24, 1214–1225 (2019) applications: a survey. Expert Syst. Appl. 42(21), 7684–7697
48. Krishnaveni, H., Janita, V.S.: Completion time based sufferage (2015)
algorithm for static task scheduling in cloud environment. Int. 67. Zames, G.: Genetic algorithms in search, optimization and
J. Pure Appl. Math. 119(12), 13793–13797 (2018) machine learning. Inf Tech J 3(1), 301 (1981)
49. Dutta, M. and Aggarwal, N., 2016. Meta-heuristics based 68. Dasgupta, K., Mandal, B., Dutta, P., Mandal, J.K., Dam, S.: A
approach for workflow scheduling in cloud computing: a survey. genetic algorithm (ga) based load balancing strategy for cloud
In Artificial Intelligence and Evolutionary Computations in computing. Procedia Technol. 10, 340–347 (2013)
Engineering Systems: Proceedings of ICAIECES 2015 (pp. 69. Ge, Y. and Wei, G., 2010, October. GA-based task scheduler for the
1331–1345). Springer India. cloud computing systems. In 2010 International Conference on Web
50. Wu, F., Wu, Q., Tan, Y.: Workflow scheduling in cloud: a Information Systems and Mining (Vol. 2, pp. 181–186). IEEE.
survey. J. Supercomput. 71, 3373–3418 (2015) 70. Zheng, Z., Wang, R., Zhong, H. and Zhang, X., 2011, March. An
51. Alkhanak, E.N., Lee, S.P., Khan, S.U.R.: Cost-aware challenges approach for cloud resource scheduling based on Parallel Genetic
for workflow scheduling approaches in cloud computing envi- Algorithm. In 2011 3rd International Conference on Computer
ronments: Taxonomy and opportunities. Futur. Gener. Comput. Research and Development (Vol. 2, pp. 444–447). IEEE.
Syst. 50, 3–21 (2015) 71. Wang, T., Liu, Z., Chen, Y., Xu, Y. and Dai, X., 2014, August.
52. Masdari, M., ValiKardan, S., Shahi, Z., Azar, S.I.: Towards Load balancing task scheduling based on genetic algorithm in
workflow scheduling in cloud computing: a comprehensive cloud computing. In 2014 IEEE 12th international conference
analysis. J. Netw. Comput. Appl. 66, 64–82 (2016) on dependable, autonomic and secure computing (pp. 146–152).
53. Fister, I., Jr., Yang, X.S., Fister, I., Brest, J., Fister, D.: A brief IEEE.
review of nature-inspired algorithms for optimization. Neural 72. Jang, S.H., Kim, T.Y., Kim, J.K., Lee, J.S.: The study of genetic
Evol. Comput. (2013). https://doi.org/10.48550/arXiv.1307. algorithm-based task scheduling for cloud computing. Int.
4186 J. Cont. Autom. 5(4), 157–162 (2012)
54 Yang, X.S., He, X.: Nature-inspired optimization algorithms in 73. Liu, J., Luo, X.G., Zhang, X.M., Zhang, F., Li, B.N.: Job
engineering: overview and applications. Nat. -Inspired Comput. scheduling model for cloud computing based on multi-objective
Eng. (2016). https://doi.org/10.1007/978-3-319-30235-5_1 genetic algorithm. Int. J. Comput. Sci. Issues (IJCSI) 10(1), 134
55. Nanda, S.J., Panda, G.: A survey on nature inspired meta- (2013)
heuristic algorithms for partitional clustering. Swarm Evol. 74. Kaur, K., Chhabra, A., Singh, G.: Heuristics based genetic
Comput. 16, 1–18 (2014) algorithm for scheduling static tasks in homogeneous parallel
56. Ss, V.C., Hs, A.: Nature inspired meta heuristic algorithms for system. Int. J. Comput. Sci. Security (IJCSS) 4(2), 183–198
optimization problems. Computing 104(2), 251–269 (2022) (2010)
57 Mirjalili, S., Mirjalili, S.: Genetic algorithm. Evol. Algorithms 75. Ghorbannia Delavar, A., Aryan, Y.: HSGA: a hybrid heuristic
Neural Netw.: Theory Appl. 780, 43–55 (2019) algorithm for workflow scheduling in cloud systems. Clust.
58. Wang, Z., Tang, K., Yao, X.: A memetic algorithm for multi- Comput. 17, 129–137 (2014)
level redundancy allocation. IEEE Trans. Reliab. 59(4), 76. Yu, J., Buyya, R.: Scheduling scientific workflow applications
754–765 (2010) with deadline and budget constraints using genetic algorithms.
59. Tilahun, S.L., Kassa, S.M. and Ong, H.C., 2012. A new algo- Sci. Program. 14(3–4), 217–230 (2006)
rithm for multilevel optimization problems using evolutionary 77. Khajemohammadi, H., Fanian, A. and Gulliver, T.A., 2013,
strategy, inspired by natural adaptation. In PRICAI 2012: August. Fast workflow scheduling for grid computing based on a
Trends in Artificial Intelligence: 12th Pacific Rim International multi-objective genetic algorithm. In 2013 IEEE Pacific Rim
Conference on Artificial Intelligence, Kuching, Malaysia, Conference on Communications, Computers and Signal Pro-
cessing (PACRIM) (pp. 96–101). IEEE.

123
 Cluster Computing

78. Gu, J., Hu, J., Zhao, T., Sun, G.: A new resource scheduling shop scheduling problem in order to minimize maximum com-
strategy based on genetic algorithm in cloud computing envi- pletion time. Int. J. Comput. Appl. 28(10), 27–32 (2011)
ronment. J. Comput. 7(1), 42–52 (2012) 96. Madani-Isfahani, M., Ghobadian, E., Tekmehdash, H., Tavak-
79. Huang, J.: The workflow task scheduling algorithm based on the koli-Moghaddam, R., Naderi-Beni, M.: An imperialist compet-
GA model in the cloud computing environment. J. Softw. 9(4), itive algorithm for a bi-objective parallel machine scheduling
873–880 (2014) problem with load balancing consideration. Int. J. Ind. Eng.
80. Nasonov, D., Butakov, N., Balakhontseva, M., Knyazkov, K. Comput. 4(2), 191–202 (2013)
and Boukhanovsky, A.V., 2014. Hybrid evolutionary workflow 97. Yakhchi, S., Ghafari, S.M., Yakhchi, M., Fazeli, M. and
scheduling algorithm for dynamic heterogeneous distributed Patooghy, A., 2015, March. ICA-MMT: A load balancing
computational environment. In International Joint Conference method in cloud computing environment. In 2015 2nd World
SOCO’14-CISIS’14-ICEUTE’14: Bilbao, Spain, June 25th-27th, Symposium on Web Applications and Networking
2014, Proceedings (pp. 83–92). Springer International (WSWAN) (pp. 1–7). IEEE.
Publishing. 98. Yousefyan, S., Dastjerdi, A.V. and Salehnamadi, M.R., 2013,
81. Szabo, C., Sheng, Q.Z., Kroeger, T., Zhang, Y., Yu, J.: Science May. Cost effective cloud resource provisioning with imperialist
in the cloud: allocation and execution of data-intensive scientific competitive algorithm optimization. In The 5th Conference on
workflows. J. Grid Comput. 12, 245–264 (2014) Information and Knowledge Technology (pp. 55–60). IEEE.
82. Shen, G. and Zhang, Y.Q., 2011. A shadow price guided genetic 99. Pooranian, Z., Shojafar, M., Javadi, B., Abraham, A.: Using
algorithm for energy aware task scheduling on cloud computers. imperialist competition algorithm for independent task
In Advances in Swarm Intelligence: Second International Con- scheduling in grid computing. J. Intell. Fuzzy Syst. 27(1),
ference, ICSI 2011, Chongqing, China, June 12-15, 2011, Pro- 187–199 (2014)
ceedings, Part I 2 (pp. 522-529). Springer Berlin Heidelberg. 100. Piroozfard, H. and Wong, K.Y., 2014, December. An imperialist
83. Kolodziej, J., Khan, S.U. and Xhafa, F., 2011, October. Genetic competitive algorithm for the job shop scheduling problems.
algorithms for energy-aware scheduling in computational grids. In 2014 IEEE International Conference on Industrial Engi-
In 2011 International Conference on P2P, Parallel, Grid, Cloud neering and Engineering Management (pp. 69–73). IEEE.
and Internet Computing (pp. 17–24). IEEE. 101. Jula, A., Othman, Z. and Sundararajan, E., 2013, April. A hybrid
84. Zhu, K., Song, H., Liu, L., Gao, J. and Cheng, G., 2011, imperialist competitive-gravitational attraction search algorithm
December. Hybrid genetic algorithm for cloud computing to optimize cloud service composition. In 2013 IEEE workshop
applications. In 2011 IEEE Asia-Pacific Services Computing on memetic computing (MC) (pp. 37–43). IEEE.
Conference (pp. 182–187). IEEE. 102. Jula, A., Othman, Z., Sundararajan, E.: Imperialist competitive
85. Sawant, S., 2011. A genetic algorithm scheduling approach for algorithm with PROCLUS classifier for service time optimiza-
virtual machine resources in a cloud computing environment. tion in cloud computing service composition. Expert Syst. Appl.
86. Moscato, P.: On evolution, search, optimization, genetic algo- 42(1), 135–145 (2015)
rithms and martial arts: towards memetic algorithms. Caltech 103. Fatemipour, F. and Fatemipour, F., 2012. Scheduling scientific
Concurr. Comput. Program 826, 37 (1989) workflows using imperialist competitive algorithm. In Interna-
87. Jouglet, A., Oğuz, C., Sevaux, M.: Hybrid flow-shop: a memetic tional conference on industrial intelligent information (ICIII
algorithm using constraint-based scheduling for efficient search. 2012) (pp. 218–225).
J. Mathe. Model. Algorithms 8, 271–292 (2009) 104. Faragardi, H.R., Rajabi, A., Shojaee, R. and Nolte, T., 2013,
88. Moscato, P., Norman, M.G.: A memetic approach for the trav- November. Towards energy-aware resource scheduling to
eling salesman problem implementation of a computational maximize reliability in cloud computing systems. In 2013 IEEE
ecology for combinatorial optimization on message-passing 10th International Conference on High Performance Computing
systems. Parallel Comput. Trans. Appl. 1, 177–186 (1992) and Communications & 2013 IEEE International Conference on
89. Kashani, M.H., Jahanshahi, M.: A new method based on Embedded and Ubiquitous Computing (pp. 1469–1479). IEEE.
memetic algorithm for task scheduling in distributed systems. 105. Rajakumar, B.R.: The Lion’s Algorithm: a new nature-inspired
Int. J. Simul. Syst. Sci. Technol. 10(5), 26–32 (2009) search algorithm. Procedia Technol. 6, 126–135 (2012)
90. Padmavathi, S., Shalinie, S.M., Abhilaash, R.: A memetic 106. Yazdani, M., Jolai, F.: Lion optimization algorithm (LOA): a
algorithm based task scheduling considering communication nature-inspired metaheuristic algorithm. J. Comput. Design Eng.
cost on cluster of workstations. Int. J. Adv. Soft Comput. Appl. 3(1), 24–36 (2016)
2, 174–190 (2010) 107. Emami, H.: Cloud task scheduling using enhanced sunflower
91. Sutar, S., Sawant, J. and Jadhav, J., 2006. Task scheduling for optimization algorithm. Ict Express 8(1), 97–100 (2022)
multiprocessor systems using memetic algorithms. In 4th 108. Subhash, L.S., Udayakumar, R.: Sunflower whale optimization
International Working Conference Performance Modeling and algorithm for resource allocation strategy in cloud computing
Evaluation of Heterogeneous Networks (HET-NETs ‘06). platform. Wireless Pers. Commun. 116, 3061–3080 (2021)
92. Zhao, F., Tang, J.: A memetic algorithm combined particle 109. Chandrashekar, C., Krishnadoss, P.: Opposition based sunflower
swarm optimization with simulated annealing and its application optimization algorithm using cloud computing environments.
on multiprocessor scheduling problem. Prz Elektrotechniczny Mater. Today: Proc. 62, 4896–4902 (2022)
88, 292–296 (2012) 110. Jena, U.K., Kumar Das, P., Kabat, M.R., Kuanar, S.K.: Dynamic
93. Atashpaz-Gargari, E. and Lucas, C., 2007, September. Imperi- load balancing in cloud network through sunflower optimization
alist competitive algorithm: an algorithm for optimization algorithm and sine-cosine algorithm. In: Next generation of
inspired by imperialistic competition. In 2007 IEEE Congress internet of things: proceedings of ICNGIoT 2022, pp. 609–621.
on Evolutionary Computation (pp. 4661–4667). Ieee. Springer Nature Singapore, Singapore (2022)
94. Behnamian, J., Zandieh, M.: A discrete colonial competitive 111. Mahale, R.A., Chavan, S.D.: A survey: evolutionary and swarm
algorithm for hybrid flowshop scheduling to minimize earliness based bio-inspired optimization algorithms. Int. J. Sci. Res.
and quadratic tardiness penalties. Expert Syst. Appl. 38(12), Publ. 2(12), 1–6 (2012)
14490–14498 (2011) 112. Juneja, M. and Nagar, S.K., 2016, October. Particle swarm
95. Attar, S.F., Mohammadi, M., Tavakkoli-Moghaddam, R.: A optimization algorithm and its parameters: A review. In 2016
novel imperialist competitive algorithm to solve flexible flow

123
Cluster Computing

International Conference on Control, Computing, Communica- 131. Dorigo, M., Blum, C.: Ant colony optimization theory: a survey.
tion and Materials (ICCCCM) (pp. 1–5). IEEE. Theoret. Comput. Sci. 344(2–3), 243–278 (2005)
113. Yuce, B., Packianather, M.S., Mastrocinque, E., Pham, D.T., 132. Chiang, C.W., Lee, Y.C., Lee, C.N., Chou, T.Y.: Ant colony
Lambiase, A.: Honey bees inspired optimization method: the optimisation for task matching and scheduling. IEE Proc. –
bees algorithm. Insects 4(4), 646–662 (2013) Comput. Digital Tech. 153(6), 373–380 (2006)
114. Mirjalili, S., Lewis, A.: The whale optimization algorithm. Adv. 133. Chen, W.N., Zhang, J. and Yu, Y., 2007, September. Workflow
Eng. Softw. 95, 51–67 (2016) scheduling in grids: an ant colony optimization approach.
115. Senthilnath, J., Omkar, S.N., Mani, V.: Clustering using firefly In 2007 IEEE Congress on Evolutionary Computation (pp.
algorithm: performance study. Swarm Evol. Comput. 1(3), 3308–3315). IEEE.
164–171 (2011) 134. Chen, W.N., Shi, Y. and Zhang, J., 2009, May. An ant colony
116. Karaboga, D., Basturk, B.: On the performance of artificial bee optimization algorithm for the time-varying workflow schedul-
colony (ABC) algorithm. Appl. Soft Comput. 8(1), 687–697 ing problem in grids. In 2009 IEEE Congress on Evolutionary
(2008) Computation (pp. 875–880). IEEE.
117. Blum, C.: Ant colony optimization: Introduction and recent 135. Pacini, E., Mateos, C., Garino, C.G.: Balancing throughput and
trends. Phys. Life Rev. 2(4), 353–373 (2005) response time in online scientific clouds via ant colony opti-
118. Neshat, M., Sepidnam, G., Sargolzaei, M., Toosi, A.N.: Artifi- mization (SP2013/2013/00006). Adv. Eng. Softw. 84, 31–47
cial fish swarm algorithm: a survey of the state-of-the-art, (2015)
hybridization, combinatorial and indicative applications. Artif. 136. Liu, X.F., Zhan, Z.H., Du, K.J. and Chen, W.N., 2014, July.
Intell. Rev. 42(4), 965–997 (2014) Energy aware virtual machine placement scheduling in cloud
119. Yang, X.S., He, X.: Bat algorithm: literature review and appli- computing based on ant colony optimization approach. In Pro-
cations. Int. J. Bio-inspired Comput. 5(3), 141–149 (2013) ceedings of the 2014 annual conference on genetic and evolu-
120 Ahmed, A.M., Rashid, T.A., Saeed, S.A.M.: Cat swarm opti- tionary computation (pp. 41–48).
mization algorithm: a survey and performance evaluation. 137. Sivaraju, S.S., Kumar, C.: Energy enhancement of WSN with
Comput. Intell. Neurosci. (2020). https://doi.org/10.1155/2016/ deep learning based SOM scheduling algorithm. J. Inf. Technol.
3896065 Digital World 4(3), 238–249 (2022)
121. Ajith, A., Crina, G., Vitorino, R., Martin, R., Stephen, W.: 138. Mathiyalagan, P., Suriya, S., Sivanandam, S.N.: Modified ant
Termite: a swarm intelligent routing algorithm for mobilewire- colony algorithm for grid scheduling. Int. J. Comput. Sci. Eng.
less Ad-Hoc networks, pp. 155–184. Springer, Berlin (2006) 2(02), 132–139 (2010)
122. Pinto, P., Runkler, T.A. and Sousa, J.M., 2005. Wasp swarm 139. Liu, A. and Wang, Z., 2008, October. Grid task scheduling
optimization of logistic systems. In Adaptive and Natural based on adaptive ant colony algorithm. In 2008 International
Computing Algorithms: Proceedings of the International Con- conference on management of e-commerce and e-govern-
ference in Coimbra, Portugal, 2005 (pp. 264–267). Springer ment (pp. 415–418). IEEE.
Vienna. 140. Bagherzadeh, J. and MadadyarAdeh, M., 2009, October. An
123 Chen, X., Zhou, Y., Luo, Q.: A hybrid monkey search algorithm improved ant algorithm for grid scheduling problem. In 2009
for clustering analysis. Sci. World J. (2014). https://doi.org/10. 14th International CSI Computer Conference (pp. 323–328).
1155/2014/938239 IEEE.
124. YongBo, C., YueSong, M., JianQiao, Y., XiaoLong, S., Nuo, X.: 141. Chen, W.N., Zhang, J.: An ant colony optimization approach to
Three-dimensional unmanned aerial vehicle path planning using a grid workflow scheduling problem with various QoS require-
modified wolf pack search algorithm. Neurocomputing 266, ments. IEEE Trans. Syst. Man Cybernetics Part C 39(1), 29–43
445–457 (2017) (2008)
125. Lu, X. and Zhou, Y., 2008. A novel global convergence algo- 142. Tawfeek, M.A., El-Sisi, A., Keshk, A.E. and Torkey, F.A., 2013,
rithm: bee collecting pollen algorithm. In Advanced Intelligent November. Cloud task scheduling based on ant colony opti-
Computing Theories and Applications. With Aspects of Artificial mization. In 2013 8th international conference on computer
Intelligence: 4th International Conference on Intelligent Com- engineering & systems (ICCES) (pp. 64–69). IEEE.
puting, ICIC 2008 Shanghai, China, September 15–18, 2008 143. Khambre, P.D., Deshpande, A., Mehta, A., Sain, A.: Modified
Proceedings 4 (pp. 518–525). Springer Berlin Heidelberg. pheromone update rule to implement ant colony optimization
126. Kenan Dosoglu, M., Guvenc, U., Duman, S., Sonmez, Y., Tolga algorithm for workflow scheduling algorithm problem in grids.
Kahraman, H.: Symbiotic organisms search optimization algo- Int. J. Adv. Res. Comput. Sci. Technol. 2(2), 424–429 (2014)
rithm for economic/emission dispatch problem in power sys- 144. Singh, L., Singh, S.: Deadline and cost based ant colony opti-
tems. Neural Comput. Appl. 29, 721–737 (2018) mization algorithm for scheduling workflow applications in
127. Meraihi, Y., Gabis, A.B., Ramdane-Cherif, A., Acheli, D.: A hybrid cloud. J. Sci. Eng. Res. 5(10), 1417–1420 (2014)
comprehensive survey of crow search algorithm and its appli- 145. Eberhart, R. and Kennedy, J., 1995, November. Particle swarm
cations. Artif. Intell. Rev. 54(4), 2669–2716 (2021) optimization. In Proceedings of the IEEE International Con-
128. Dhanya, D., Arivudainambi, D.: Dolphin partner optimization ference on Neural Networks (Vol. 4, pp. 1942–1948).
based secure and qualified virtual machine for resource alloca- 146. Pandey, S., Wu, L., Guru, S.M. and Buyya, R., 2010, April. A
tion with streamline security analysis. Peer-to-Peer Netw. Appl. particle swarm optimization-based heuristic for scheduling
12, 1194–1213 (2019) workflow applications in cloud computing environments.
129. Mirjalili, S., Mirjalili, S.M., Lewis, A.: Grey wolf optimizer. In 2010 24th IEEE international conference on advanced
Adv. Eng. Softw. 69, 46–61 (2014) information networking and applications (pp. 400–407). IEEE.
130. Pilla, R., Botcha, N., Gorripotu, T.S. and Azar, A.T., 2020. 147. Wu, Z., Ni, Z., Gu, L. and Liu, X., 2010, December. A revised
Fuzzy PID controller for automatic generation control of inter- discrete particle swarm optimization for cloud workflow
connected power system tuned by glow-worm swarm opti- scheduling. In 2010 international conference on computational
mization. In Applications of Robotics in Industry Using intelligence and security (pp. 184–188). IEEE.
Advanced Mechanisms: Proceedings of International Confer- 148. Xue, S.J., Wu, W.: Scheduling workflow in cloud computing
ence on Robotics and Its Industrial Applications 2019 1 (pp. based on hybrid particle swarm algorithm. Indonesian J. Electr.
140–149). Springer International Publishing. Eng. Comput. Sci. 10(7), 1560–1566 (2012)

123
 Cluster Computing

149. Tavakkoli-Moghaddam, R., Azarkish, M., Sadeghnejad-Bark- 168. Hashemi, S.M., Hanani, A.: Solving the scheduling problem in
ousaraie, A.: A new hybrid multi-objective Pareto archive PSO computational grid using artificial bee colony algorithm. Adv.
algorithm for a bi-objective job shop scheduling problem. Comput. Sci.: Int. J. 2, 37–41 (2013)
Expert Syst. Appl. 38(9), 10812–10821 (2011) 169. Mousavinasab, Z., Entezari-Maleki, R. and Movaghar, A., 2011.
150. Beegom, A.A. and Rajasree, M.S., 2014. A particle swarm A bee colony task scheduling algorithm in computational grids.
optimization based pareto optimal task scheduling in cloud In Digital Information Processing and Communications: Inter-
computing. In Advances in Swarm Intelligence: 5th Interna- national Conference, ICDIPC 2011, Ostrava, Czech Republic,
tional Conference, ICSI 2014, Hefei, China, October 17–20, July 7-9, 2011, Proceedings, Part I (pp. 200-210). Springer
2014, Proceedings, Part II 5 (pp. 79–86). Springer International Berlin Heidelberg
Publishing. 170. de Mello, R.F., Senger, L.J. and Yang, L.T., 2006, April. A
151. Karimi, M., Motameni, H.: Tasks scheduling in computational routing load balancing policy for grid computing environments.
grid using a hybrid discrete particle swarm optimization. Int. In 20th International Conference on Advanced Information
J. Grid Distrib. Comput. 6(2), 29–38 (2013) Networking and Applications-Volume 1 (AINA’06) (Vol. 1,
152. Pooranian, Z., Shojafar, M., Abawajy, J.H., Abraham, A.: An pp. 6-pp). IEEE.
efficient meta-heuristic algorithm for grid computing. J. Comb. 171 Dhinesh Babu, L.D., Krishna, P.V.: Honey bee behavior inspired
Optim. 30, 413–434 (2015) load balancing of tasks in cloud computing environments. Appl.
153. Krishnasamy, K.: Task scheduling algorithm based on hybrid Soft Comput. 13(5), 2292–2303 (2013)
particle swarm optimization in cloud computing environment. 172. Soni, A., Vishwakarma, G., Jain, Y.K.: A bee colony based
J. Theor. Appl. Inf. Technol. 55(1), 1–3 (2013) multi-objective load balancing technique for cloud computing
154. Sridhar, M. and Babu, G.R.M., 2015, June. Hybrid particle environment. Int. J. Comput. Appl. 114(4), 19–25 (2015)
swarm optimization scheduling for cloud computing. In 2015 173. Priyadarsini, R.J., Arockiam, L.: PBCOPSO: A parallel opti-
IEEE International Advance Computing Conference mization algorithm for task scheduling in cloud environment.
(IACC) (pp. 1196–1200). IEEE. Indian J. Sci. Technol. 8(16), 1–5 (2015)
155. Al-maamari, A. and Omara, F.A., 2015. Task scheduling using 174. Kashani, M.H., Jamei, M., Akbari, M. and Tayebi, R.M., 2011,
hybrid algorithm in cloud computing environments. Journal of July. Utilizing bee colony to solve task scheduling problem in
Computer Engineering (IOSR-JCE), 17(3), pp.96–106. distributed systems. In 2011 Third International Conference on
156. Zhang, L., Chen, Y., Sun, R., Jing, S., Yang, B.: A task Computational Intelligence, Communication Systems and Net-
scheduling algorithm based on PSO for grid computing. Int. works (pp. 298–303). IEEE.
J. Comput. Intell. Res. 4(1), 37–43 (2008) 175. Navimipour, N.J., 2015, June. Task scheduling in the cloud
157. Liu, H., Abraham, A., Hassanien, A.E.: Scheduling jobs on environments based on an artificial bee colony algorithm.
computational grids using a fuzzy particle swarm optimization In International Conference on Image Processing (pp. 38–44).
algorithm. Futur. Gener. Comput. Syst. 26(8), 1336–1343 (2010) 176. Hesabian, N., Haj, H., Javadi, S.: Optimal scheduling in cloud
158. Aron, R., Chana, I., Abraham, A.: A hyper-heuristic approach computing environment using the bee algorithm. Int J Comput
for resource provisioning-based scheduling in grid environment. Netw Commun Secur 3, 253–258 (2015)
J. Supercomput. 71, 1427–1450 (2015) 177. Udomkasemsub, O., Xiaorong, L. and Achalakul, T., 2012, May. A
159. Sidhu, M.S., Thulasiraman, P. and Thulasiram, R.K., 2013, multiple-objective workflow scheduling framework for cloud data
April. A load-rebalance PSO heuristic for task matching in analytics. In 2012 Ninth International Conference on Computer
heterogeneous computing systems. In 2013 IEEE Symposium on Science and Software Engineering (JCSSE) (pp. 391–398). IEEE.
Swarm Intelligence (SIS) (pp. 180–187). IEEE. 178. Liang, Y.C., Chen, A.H.L. and Nien, Y.H., 2014, July. Artificial
160. Ramezani, F., Lu, J., Hussain, F.K.: Task-based system load bee colony for workflow scheduling. In 2014 IEEE Congress on
balancing in cloud computing using particle swarm optimiza- Evolutionary Computation (CEC) (pp. 558–564). IEEE.
tion. Int. J. Parallel Prog. 42, 739–754 (2014) 179. Kansal, N.J., Chana, I.: Artificial bee colony based energy-aware
161. Milani, F.S., Navin, A.H.: Multi-objective task scheduling in the resource utilization technique for cloud computing. Concurr.
cloud computing based on the Patrice swarm optimization. Int. Comput.: Practice Exp. 27(5), 1207–1225 (2015)
J. Inf. Technol. Comput. Sci. 7(5), 61–66 (2015) 180. Hasançebi, O., Teke, T., Pekcan, O.: A bat-inspired algorithm
162. Wang, Z., Shuang, K., Yang, L., Yang, F.: Energy-aware and for structural optimization. Comput. Struct. 128, 77–90 (2013)
revenue-enhancing combinatorial scheduling in virtualized of 181. Jacob, L.: Bat algorithm for resource scheduling in cloud
cloud datacenter. J. Converg. Inf. Technol. 7(1), 62–70 (2012) computing. Population 5(18), 23 (2014)
163. Karaboga, D., 2005. An idea based on honey bee swarm for 182. Kumar, V.S., Aramudhan, M.: Trust based resource selection in
numerical optimization (Vol. 200, pp. 1–10). Technical report- cloud computing using hybrid algorithm. Int. J. Intell. Syst.
tr06, Erciyes university, engineering faculty, computer engi- Appl. 7(8), 59 (2015)
neering department. 183. Kumar, V.S.: Hybrid optimized list scheduling and trust based
164. Liu, Y.F., Liu, S.Y.: A hybrid discrete artificial bee colony resource selection in cloud computing. J. Theor. Appl. Inf.
algorithm for permutation flowshop scheduling problem. Appl. Technol. 69(3), 434–442 (2014)
Soft Comput. 13(3), 1459–1463 (2013) 184. Raghavan, S., Sarwesh, P., Marimuthu, C. and Chandrasekaran,
165. Huang, Y.M., Lin, J.C.: A new bee colony optimization algo- K., 2015, January. Bat algorithm for scheduling workflow
rithm with idle-time-based filtering scheme for open shop- applications in cloud. In 2015 International Conference on
scheduling problems. Expert Syst. Appl. 38(5), 5438–5447 Electronic Design, Computer Networks & Automated Verifica-
(2011) tion (EDCAV) (pp. 139–144). IEEE.
166. Ziarati, K., Akbari, R., Zeighami, V.: On the performance of bee 185. George, S.: Hybrid PSO-MOBA for profit maximization in cloud
algorithms for resource-constrained project scheduling problem. computing. Int J Adv Comput Sci Appl 6(2), 159–163 (2015)
Appl. Soft Comput. 11(4), 3720–3733 (2011) 186. Chu, S.C., Tsai, P.W. and Pan, J.S., 2006. Cat swarm opti-
167. Karaboga, D. and Gorkemli, B., 2011, June. A combinatorial mization. In PRICAI 2006: Trends in Artificial Intelligence: 9th
artificial bee colony algorithm for traveling salesman problem. Pacific Rim International Conference on Artificial Intelligence
In 2011 International Symposium on Innovations in Intelligent Guilin, China, August 7–11, 2006 Proceedings 9 (pp. 854–858).
Systems and Applications (pp. 50–53). IEEE. Springer Berlin Heidelberg.

123
Cluster Computing

187. Chu, S.C., Tsai, P.W.: Computational intelligence based on the Conference on Emerging Trends in Engineering (ICETE), Vol.
behavior of cats. Int. J. Innov. Comput. Inf. Control 3(1), 2 (pp. 678–687). Springer International Publishing.
163–173 (2007) 205. Kashikolaei, S.M.G., Hosseinabadi, A.A.R., Saemi, B., Shareh,
188. Tsai, P.W., Pan, J.S., Chen, S.M., Liao, B.Y. and Hao, S.P., M.B., Sangaiah, A.K., Bian, G.B.: An enhancement of task
2008, July. Parallel cat swarm optimization. In 2008 interna- scheduling in cloud computing based on imperialist competitive
tional conference on machine learning and cybernetics (Vol. 6, algorithm and firefly algorithm. J. Supercomput. 76, 6302–6329
pp. 3328–3333). IEEE. (2020)
189. Pradhan, P.M., Panda, G.: Solving multiobjective problems 206 Fanian, F., Bardsiri, V.K., Shokouhifar, M.: A new task
using cat swarm optimization. Expert Syst. Appl. 39(3), scheduling algorithm using firefly and simulated annealing
2956–2964 (2012) algorithms in cloud computing. Int. J. Adv. Comput. Sci. Appl.
190. Sharafi, Y., Khanesar, M.A. and Teshnehlab, M., 2013, (2018). https://doi.org/10.14569/IJACSA.2018.090228
September. Discrete binary cat swarm optimization algorithm. 207. Du, Y., Wang, J.L., Lei, L.: Multi-objective scheduling of cloud
In 2013 3rd IEEE international conference on computer, control manufacturing resources through the integration of cat swarm
and communication (IC4) (pp. 1–6). IEEE. optimization and firefly algorithm. Adv. Prod. Eng. Manag.
191. Bilgaiyan, S., Sagnika, S. and Das, M., 2014, February. Work- (2019). https://doi.org/10.14743/apem2019.3.331
flow scheduling in cloud computing environment using cat 208. Ammari, A.C., Labidi, W., Mnif, F., Yuan, H., Zhou, M., Sarrab,
swarm optimization. In 2014 IEEE International Advance M.: Firefly algorithm and learning-based geographical task
Computing Conference (IACC) (pp. 680–685). IEEE. scheduling for operational cost minimization in distributed
192. Rouhi, S. and Nejad, E.B., 2015. CSO-GA: a new scheduling green data centers. Neurocomputing 490, 146–162 (2022)
technique for cloud computing systems based on cat swarm 209 Zolghadr-Asli, B., Bozorg-Haddad, O., Chu, X.: Crow search
optimization and genetic algorithm. Fen Bilimleri Dergisi algorithm (CSA). Adv. Optim. Nat. -inspired Algorithms (2018).
(CFD), 36(4). https://doi.org/10.1007/978-981-10-5221-7_14
193. Hof, P.R., Van der Gucht, E.: Structure of the cerebral cortex of 210. Prasanna Kumar, K.R., Kousalya, K.: Amelioration of task
the humpback whale, Megaptera novaeangliae (Cetacea, Mys- scheduling in cloud computing using crow search algorithm.
ticeti, Balaenopteridae). Anat. Rec.: Adv. Integr. Anat. Evolut. Neural Comput. Appl. 32, 5901–5907 (2020)
Biol.: Adv. Integr. Anat. Evolut. Biol. 290(1), 1–31 (2007) 211. Kumar, K.P., Kousalya, K., Vishnuppriya, S., Ponni, S. and
194. Mangalampalli, S., Karri, G.R., Kose, U.: Multi Objective Trust Logeswaran, K., 2021, February. Enhanced Crow Search
aware task scheduling algorithm in cloud computing using Algorithm for Task Scheduling in Cloud Computing. In IOP
whale optimization. J. King Saud Univ.-Comput. Inf. Sci. 35(2), Conference Series: Materials Science and Engineering (Vol.
791–809 (2023) 1055, No. 1, p. 012102). IOP Publishing.
195. Mangalampalli, S., Swain, S.K., Mangalampalli, V.K.: Priori- 212. Singh, H., Tyagi, S., Kumar, P.: Crow–penguin optimizer for
tized energy efficient task scheduling algorithm in cloud com- multiobjective task scheduling strategy in cloud computing. Int.
puting using whale optimization algorithm. Wireless Pers. J. Commun. Syst. 33(14), e4467 (2020)
Commun. 126(3), 2231–2247 (2022) 213. Singh, H., Tyagi, S., Kumar, P.: Crow search based scheduling
196. Sreenu, K., Sreelatha, M.: W-Scheduler: whale optimization for algorithm for load balancing in cloud environment. Int. J. Innov.
task scheduling in cloud computing. Clust. Comput. 22, Technol. Explor. Eng. (IJITEE) 8(9), 1058–1064 (2019)
1087–1098 (2019) 214. Singh, H., Tyagi, S., Kumar, P.: Cloud resource mapping
197. Chen, X., Cheng, L., Liu, C., Liu, Q., Liu, J., Mao, Y., Murphy, J.: A through crow search inspired metaheuristic load balancing
WOA-based optimization approach for task scheduling in cloud technique. Comput. Electr. Eng. 93, 107221 (2021)
computing systems. IEEE Syst. J. 14(3), 3117–3128 (2020) 215 Wang, J.: Grey wolf optimization and crow search algorithm for
198. Jia, L., Li, K., Shi, X.: Cloud computing task scheduling model resource allocation scheme in cloud computing: grey wolf
based on improved whale optimization algorithm. Wirel. Com- optimization and crow search algorithm in cloud computing.
mun. Mob. Comput. 2021, 1–13 (2021) Multime’d. Res. (2021). https://doi.org/10.46253/j.mr.v4i3.a3
199. Masadeh, R., Sharieh, A., Mahafzah, B.: Humpback whale 216 Kak, S.M., Agarwal, P., Alam, M.A., Siddiqui, F.: A hybridized
optimization algorithm based on vocal behavior for task approach for minimizing energy in cloud computing. Clus.
scheduling in cloud computing. Int. J. Adv. Sci. Technol. 13(3), Comput. (2022). https://doi.org/10.1007/s10586-022-03807-9
121–140 (2019) 217. Mangalampalli, S., Mangalampalli, V.K. and Swain, S.K., A
200 Arora, S., Singh, S.: The firefly optimization algorithm: con- Task scheduling approach in cloud computing to minimize the
vergence analysis and parameter selection. Int. J. Comp. Appl. power cost in datacenters using crow search.
(2013). https://doi.org/10.5120/11826-7528 218. Joshi, A.S., Kulkarni, O., Kakandikar, G.M., Nandedkar, V.M.:
201. Mangalampalli, S., Karri, G.R., Elngar, A.A.: An efficient trust- Cuckoo search optimization-a review. Mater. Today: Proc. 4(8),
aware task scheduling algorithm in cloud computing using 7262–7269 (2017)
firefly optimization. Sensors 23(3), 1384 (2023) 219. Elnahary, M.K., Hamed, A.Y., El-Sayed, H.: Task scheduling
202. Ebadifard, F., Doostali, S. and Babamir, S.M., 2018, December. optimization in cloud computing by cuckoo search algorithm.
A firefly-based task scheduling algorithm for the cloud com- Sohag J. Sci. 7(3), 29–37 (2022)
puting environment: Formal verification and simulation analy- 220. Navimipour, N.J., Milani, F.S.: Task scheduling in the cloud
ses. In 2018 9th International Symposium on computing based on the cuckoo search algorithm. Int. J. Model.
Telecommunications (IST) (pp. 664–669). IEEE. Optim. 5(1), 44 (2015)
203. Malleswaran, S.K.A., Kasireddi, B.: An efficient task scheduling 221. Prem Jacob, T., Pradeep, K.: A multi-objective optimal task
method in a cloud computing environment using firefly crow scheduling in cloud environment using cuckoo particle swarm
search algorithm (FF-CSA). Int. J. Sci. Technol. Res. 8(12), optimization. Wireless Pers. Commun. 109, 315–331 (2019)
623–627 (2019) 222. Krishnadoss, P., Pradeep, N., Ali, J., Nanjappan, M., Krish-
204. Rajagopalan, A., Modale, D.R. and Senthilkumar, R., 2020. namoorthy, P., Kedalu Poornachary, V.: CCSA: Hybrid cuckoo
Optimal scheduling of tasks in cloud computing using hybrid crow search algorithm for task scheduling in cloud computing.
firefly-genetic algorithm. In Advances in Decision Sciences, Int. J. Intell. Eng. Syst. 14(4), 241–250 (2021)
Image Processing, Security and Computer Vision: International

123
 Cluster Computing

223. Agarwal, M. and Srivastava, G.M.S., 2018. A cuckoo search algorithm for workflow scheduling in green cloud computing.
algorithm-based task scheduling in cloud computing. In Ad- Evol. Intel. 14, 1997–2025 (2021)
vances in Computer and Computational Sciences: Proceedings 240. Arora, N., Banyal, R.K.: A particle grey wolf hybrid algorithm
of ICCCCS 2016, Volume 2 (pp. 293–299). Springer Singapore. for workflow scheduling in cloud computing. Wireless Pers.
224. Nazir, S., Shafiq, S., Iqbal, Z., Zeeshan, M., Tariq, S. and Javaid, Commun. 122(4), 3313–3345 (2022)
N., 2019. Cuckoo optimization algorithm based job scheduling 241. Balasubramanian, K., Ramya, K., Devi, K.G.: Improved swarm
using cloud and fog computing in smart grid. In Advances in optimization of deep features for glaucoma classification using
Intelligent Networking and Collaborative Systems: The 10th SEGSO and VGGNet. Biomed. Signal Process. Control 77,
International Conference on Intelligent Networking and Col- 103845 (2022)
laborative Systems (INCoS-2018) (pp. 34–46). Springer Inter- 242. Zhou, J., Dong, S.: Hybrid glowworm swarm optimization for
national Publishing. task scheduling in the cloud environment. Eng. Optim. 50(6),
225. Gawali, M.B., Shinde, S.K.: Standard deviation based modified 949–964 (2018)
cuckoo optimization algorithm for task scheduling to efficient 243. Alboaneen, D.A., Tianfield, H. and Zhang, Y., 2017, March.
resource allocation in cloud computing. J. Adv. Inf. Technol. 8, Glowworm swarm optimisation based task scheduling for cloud
4 (2017) computing. In Proceedings of the Second International Con-
226. Madni, S.H.H., Latiff, M.S.A., Ali, J., Abdulhamid, S.I.M.: ference on Internet of things, Data and Cloud Computing (pp.
Multi-objective-oriented cuckoo search optimization-based 1–7).
resource scheduling algorithm for clouds. Arab. J. Sci. Eng. 44, 244. Abdullahi, M., Ngadi, M.A.: Symbiotic organism search opti-
3585–3602 (2019) mization based task scheduling in cloud computing environ-
227. Krishnadoss, P., Jacob, P.: OCSA: task scheduling algorithm in ment. Futur. Gener. Comput. Syst. 56, 640–650 (2016)
cloud computing environment. Int. J. Intell. Eng. Syst. 11(3), 245 Sa’ad, S., Muhammed, A., Abdullahi, M., Abdullah, A., Hakim
271–279 (2018) Ayob, F.: An enhanced discrete symbiotic organism search
228. Madni, S.H.H., Abd Latiff, M.S., Abdulhamid, S.I.M., Ali, J.: algorithm for optimal task scheduling in the cloud. Algorithms
Hybrid gradient descent cuckoo search (HGDCS) algorithm for 14(7), 200 (2021)
resource scheduling in IaaS cloud computing environment. 246. Abdullahi, M., Ngadi, M.A., Dishing, S.I., Ahmad, B.I.E.: An
Clust. Comput. 22, 301–334 (2019) efficient symbiotic organisms search algorithm with chaotic
229. Pradeep, K., Prem Jacob, T.: A hybrid approach for task optimization strategy for multi-objective task scheduling prob-
scheduling using the cuckoo and harmony search in cloud lems in cloud computing environment. J. Netw. Comput. Appl.
computing environment. Wireless Pers. Commun. 101, 133, 60–74 (2019)
2287–2311 (2018) 247 Abdullahi, M., Ngadi, M.A., Dishing, S.I., Abdulhamid, S.I.M.:
230. Shahdi-Pashaki, S., Teymourian, E., Kayvanfar, V., Komaki, An adaptive symbiotic organisms search for constrained task
G.M., Sajadi, A.: Group technology-based model and cuckoo scheduling in cloud computing. J. Ambient Intell. Humanized
optimization algorithm for resource allocation in cloud com- Comput. (2022). https://doi.org/10.1007/s12652-021-03632-9
puting. IFAC-PapersOnLine 48(3), 1140–1145 (2015) 248. Sharma, M. and Verma, A., 2017, February. Energy-aware
231. Durgadevi, P., Srinivasan, S.: Resource allocation in cloud discrete symbiotic organism search optimization algorithm for
computing using SFLA and cuckoo search hybridization. Int. task scheduling in a cloud environment. In 2017 4th Interna-
J. Parallel Prog. 48, 549–565 (2020) tional Conference on Signal Processing and Integrated Net-
232. Faris, H., Aljarah, I., Al-Betar, M.A., Mirjalili, S.: Grey wolf works (SPIN) (pp. 513–518). IEEE.
optimizer: a review of recent variants and applications. Neural 249. Zubair, A.A., Razak, S.A., Ngadi, M.A., Al-Dhaqm, A., Yafooz,
Comput. Appl. 30, 413–435 (2018) W.M., Emara, A.H.M., Saad, A., Al-Aqrabi, H.: A cloud com-
233. Natesan, G., Chokkalingam, A.: An improved grey wolf opti- puting-based modified symbiotic organisms search algorithm
mization algorithm based task scheduling in cloud computing (AI) for optimal task scheduling. Sensors 22(4), 1674 (2022)
environment. Int. Arab J. Inf. Technol. 17(1), 73–81 (2020) 250. Siddique, N., Adeli, H.: Physics-based search and optimization:
234. Sreenu, K., Malempati, S.: MFGMTS: Epsilon constraint-based Inspirations from nature. Expert. Syst. 33(6), 607–623 (2016)
modified fractional grey wolf optimizer for multi-objective task 251. Hashim, F.A., Houssein, E.H., Mabrouk, M.S., Al-Atabany, W.,
scheduling in cloud computing. IETE J. Res. 65(2), 201–215 Mirjalili, S.: Henry gas solubility optimization: a novel physics-
(2019) based algorithm. Futur. Gener. Comput. Syst. 101, 646–667
235. Bacanin, N., Bezdan, T., Tuba, E., Strumberger, I., Tuba, M. and (2019)
Zivkovic, M., 2019, November. Task scheduling in cloud 252 Aarts, E., Korst, J., Michiels, W.: Simulated annealing. Search
computing environment by grey wolf optimizer. In 2019 27th Methodol.: Introd. Tutor. Optim. Decis. Support Techn. (2005).
telecommunications forum (TELFOR) (pp. 1–4). IEEE. https://doi.org/10.1007/0-387-28356-0_7
236. Gobalakrishnan, N., Arun, C.: A new multi-objective optimal 253. Rashedi, E., Rashedi, E., Nezamabadi-Pour, H.: A comprehen-
programming model for task scheduling using genetic gray wolf sive survey on gravitational search algorithm. Swarm Evol.
optimization in cloud computing. Comput. J. 61(10), 1523–1536 Comput. 41, 141–158 (2018)
(2018) 254. Erol, O.K., Eksin, I.: A new optimization method: big bang–big
237. Natesan, G., Chokkalingam, A.: Task scheduling in heteroge- crunch. Adv. Eng. Softw. 37(2), 106–111 (2006)
neous cloud environment using mean grey wolf optimization 255. Rashedi, E., Nezamabadi-Pour, H., Saryazdi, S.: GSA: a gravi-
algorithm. ICT Express 5(2), 110–114 (2019) tational search algorithm. Inf. Sci. 179(13), 2232–2248 (2009)
238. Natesha, B.V., Sharma, N.K., Domanal, S. and Guddeti, R.M.R., 256. Kaveh, A., Talatahari, S.: A novel heuristic optimization
2018, September. GWOTS: grey wolf optimization based task method: charged system search. Acta Mech. 213(3–4), 267–289
scheduling at the green cloud data center. In 2018 14th Inter- (2010)
national Conference on Semantics, Knowledge and Grids 257. Formato, R.A.: Central force optimization: a new deterministic
(SKG) (pp. 181–187). IEEE. gradient-like optimization metaheuristic. Opsearch 46(1), 25–51
239. Mohammadzadeh, A., Masdari, M., Gharehchopogh, F.S., (2009)
Jafarian, A.: Improved chaotic binary grey wolf optimization

123
Cluster Computing

258. Alatas, B.: ACROA: artificial chemical reaction optimization availability requirements and cost constraints in multi-cloud
algorithm for global optimization. Expert Syst. Appl. 38(10), environments. In 2011 Fourth IEEE International Conference
13170–13180 (2011) on Utility and Cloud Computing (pp. 267–274). IEEE.
259. Hatamlou, A.: Black hole: a new heuristic optimization 276. Cui, H., Li, Y., Liu, X., Ansari, N., Liu, Y.: Cloud service
approach for data clustering. Inf. Sci. 222, 175–184 (2013) reliability modelling and optimal task scheduling. IET Commun.
260. Kaveh, A., Khayatazad, M.: A new meta-heuristic method: ray 11(2), 161–167 (2017)
optimization. Comput. Struct. 112, 283–294 (2012) 277. Tao, F., Feng, Y., Zhang, L., Liao, T.W.: CLPS-GA: a case
261. Abd Elaziz, M., Attiya, I.: An improved Henry gas solubility library and pareto solution-based hybrid genetic algorithm for
optimization algorithm for task scheduling in cloud computing. energy-aware cloud service scheduling. Appl. Soft Comput. 19,
Artif. Intell. Rev. 54, 3599–3637 (2021) 264–279 (2014)
262. Wen, X., Huang, M. and Shi, J., 2012, October. Study on 278. Goyal, A. and Chahal, N.S., 2015, November. Bio inspired
resources scheduling based on ACO allgorithm and PSO algo- approach for load balancing to reduce energy consumption in
rithm in cloud computing. In 2012 11th International Sympo- cloud data center. In 2015 Communication, Control and Intel-
sium on Distributed Computing and Applications to Business, ligent Systems (CCIS) (pp. 406–410). IEEE.
Engineering & Science (pp. 219–222). IEEE. 279. Meshkati, J., Safi-Esfahani, F.: Energy-aware resource utiliza-
263. Mathiyalagan, P., Sivanandam, S.N., Saranya, K.S.: Hybridiza- tion based on particle swarm optimization and artificial bee
tion of modified ant colony optimization and intelligent water colony algorithms in cloud computing. J. Supercomput. 75(5),
drops algorithm for job scheduling in computational grid. 2455–2496 (2019)
ICTACT J. Soft Comput. 4(1), 651–655 (2013) 280. Meena, J., Kumar, M., Vardhan, M.: Cost effective genetic
264. Cho, K.M., Tsai, P.W., Tsai, C.W., Yang, C.S.: A hybrid meta- algorithm for workflow scheduling in cloud under deadline
heuristic algorithm for VM scheduling with load balancing in constraint. IEEE Access 4, 5065–5082 (2016)
cloud computing. Neural Comput. Appl. 26, 1297–1309 (2015) 281. Nasr, A.A., El-Bahnasawy, N.A., Attiya, G., El-Sayed, A.: Cost-
265. Madivi, R. and Kamath, S.S., 2014, July. An hybrid bio-inspired effective algorithm for workflow scheduling in cloud computing
task scheduling algorithm in cloud environment. In Fifth Inter- under deadline constraint. Arab. J. Sci. Eng. 44, 3765–3780
national Conference on Computing, Communications and Net- (2019)
working Technologies (ICCCNT) (pp. 1–7). IEEE. 282. Wu, Z., Liu, X., Ni, Z., Yuan, D., Yang, Y.: A market-oriented
266. Singhal, U., Jain, S.: A new fuzzy logic and GSO based load hierarchical scheduling strategy in cloud workflow systems.
balancing mechanism for public cloud. Int. J. Grid Distrib. J. Supercomput. 63, 256–293 (2013)
Comput. 7(5), 97–110 (2014) 283. Gabi, D., Zainal, A., Ismail, A.S. and Zakaria, Z., 2017, May.
267. Mandal, T. and Acharyya, S., 2015, December. Optimal task Scalability-Aware scheduling optimization algorithm for multi-
scheduling in cloud computing environment: meta heuristic objective cloud task scheduling problem. In 2017 6th ICT
approaches. In 2015 2nd International Conference on Electrical International Student Project Conference (ICT-ISPC) (pp. 1–6).
Information and Communication Technologies (EICT) (pp. IEEE.
24–28). IEEE. 284. Yassa, S., Chelouah, R., Kadima, H., Granado, B.: Multi-ob-
268. Ramezani, F., Lu, J. and Hussain, F., 2013. Task scheduling jective approach for energy-aware workflow scheduling in cloud
optimization in cloud computing applying multi-objective par- computing environments. Sci. World J. (2013). https://doi.org/
ticle swarm optimization. In Service-Oriented Computing: 11th 10.1155/2013/3509345
International Conference, ICSOC 2013, Berlin, Germany, 285. Li, Z., Ge, J., Yang, H., Huang, L., Hu, H., Hu, H., Luo, B.: A
December 2-5, 2013, Proceedings 11 (pp. 237-251). Springer security and cost aware scheduling algorithm for heterogeneous
Berlin Heidelberg. tasks of scientific workflow in clouds. Futur. Gener. Comput.
269. Ramezani, F., Lu, J., Taheri, J., Hussain, F.K.: Evolutionary Syst. 65, 140–152 (2016)
algorithm-based multi-objective task scheduling optimization 286. Wen, Y., Liu, J., Dou, W., Xu, X., Cao, B., Chen, J.: Scheduling
model in cloud environments. World Wide Web 18, 1737–1757 workflows with privacy protection constraints for big data
(2015) applications on cloud. Futur. Gener. Comput. Syst. 108,
270. Zuo, L., Shu, L., Dong, S., Zhu, C., Hara, T.: A multi-objective 1084–1091 (2020)
optimization scheduling method based on the ant colony algo- 287. Sharma, M., Garg, R.: HIGA: Harmony-inspired genetic algo-
rithm in cloud computing. Ieee Access 3, 2687–2699 (2015) rithm for rack-aware energy-efficient task scheduling in cloud
271. He, H., Xu, G., Pang, S., Zhao, Z.: AMTS: Adaptive multi- data centers. Eng. Sci. Technol. Int. J. 23(1), 211–224 (2020)
objective task scheduling strategy in cloud computing. China 288. Thanka, M.R., Uma Maheswari, P., Edwin, E.B.: An improved
Commun. 13(4), 162–171 (2016) efficient: artificial bee colony algorithm for security and QoS
272. Raju, R., Babukarthik, R.G., Chandramohan, D., Dhavachelvan, aware scheduling in cloud computing environment. Clust.
P. and Vengattaraman, T., 2013, February. Minimizing the Comput. 22, 10905–10913 (2019)
makespan using Hybrid algorithm for cloud computing. In 2013 289. Maurya, A.K. and Tripathi, A.K., 2018, March. Deadline-con-
3rd IEEE International Advance Computing Conference strained algorithms for scheduling of bag-of-tasks and work-
(IACC) (pp. 957–962). IEEE. flows in cloud computing environments. In Proceedings of the
273. Khalili, A. and Babamir, S.M., 2015, May. Makespan 2nd International Conference on High Performance Compila-
improvement of PSO-based dynamic scheduling in cloud envi- tion, Computing and Communications (pp. 6–10).
ronment. In 2015 23rd Iranian Conference on Electrical Engi- 290. Wu, Q., Yun, D., Lin, X., Gu, Y., Lin, W. and Liu, Y., 2013. On
neering (pp. 613–618). IEEE. workflow scheduling for end-to-end performance optimization
274. Gabi, D., Ismail, A.S. and Dankolo, N.M., 2019, June. Mini- in distributed network environments. In Job Scheduling Strate-
mized makespan based improved cat swarm optimization for gies for Parallel Processing: 16th International Workshop,
efficient task scheduling in cloud datacenter. In Proceedings of JSSPP 2012, Shanghai, China, May 25, 2012. Revised Selected
the 2019 3rd High Performance Computing and Cluster Tech- Papers 16 (pp. 76-95). Springer Berlin Heidelberg.
nologies Conference (pp. 16–20). 291. Jianfang, C., Junjie, C., Qingshan, Z.: An optimized scheduling
275. Frincu, M.E. and Craciun, C., 2011, December. Multi-objective algorithm on a cloud workflow using a discrete particle swarm.
meta-heuristics for scheduling applications with high Cybern. Inf. Technol. 14(1), 25–39 (2014)

123
 Cluster Computing

292. Sakellariou, R., Zhao, H.: A low-cost rescheduling policy for 308. Guo, P. and Xue, Z., 2017, October. Cost-effective fault-tolerant
efficient mapping of workflows on grid systems. Sci. Program. scheduling algorithm for real-time tasks in cloud systems.
12(4), 253–262 (2004) In 2017 IEEE 17th International Conference on Communication
293. Liu, K., 2009. Scheduling algorithms for instance-intensive Technology (ICCT) (pp. 1942–1946). IEEE.
cloud workflows. Swinburne University of Technology, Faculty 309. Islam, M.R. and Habiba, M., 2012, December. Dynamic
of Engineering and Industrial Sciences, Centre for Complex scheduling approach for data-intensive cloud environment.
Software Systems and Services. In 2012 International Conference on Cloud Computing Tech-
294 Wang, X., Wang, Y., Zhu, H.: Energy-efficient multi-job nologies, Applications and Management (ICCCTAM) (pp.
scheduling model for cloud computing and its genetic algorithm. 179–185). IEEE.
Math. Probl. Eng. (2012). https://doi.org/10.1155/2012/589243 310. Kumar, N. and Patel, P., 2016, March. Resource management
295. Negru, C., Pop, F., Cristea, V., Bessisy, N. and Li, J., 2013, using feed forward ANN-PSO in cloud computing environment.
September. Energy efficient cloud storage service: key issues In Proceedings of the Second International Conference on
and challenges. In 2013 Fourth International Conference on Information and Communication Technology for Competitive
Emerging Intelligent Data and Web Technologies (pp. Strategies (pp. 1–6).
763–766). IEEE. 311. Hu, H. and Wang, H., 2016, October. A prediction-based aco
296. Shu, W., Wang, W., Wang, Y.: A novel energy-efficient algorithm to dynamic tasks scheduling in cloud environment.
resource allocation algorithm based on immune clonal opti- In 2016 2nd IEEE International Conference on Computer and
mization for green cloud computing. EURASIP J. Wirel. Communications (ICCC) (pp. 2727–2732). IEEE.
Commun. Netw. 2014(1), 1–9 (2014) 312. Rahman, M., Hassan, R., Ranjan, R., Buyya, R.: Adaptive
297. Sellami, K., Ahmed-Nacer, M., Tiako, P.F., Chelouah, R.: workflow scheduling for dynamic grid and cloud computing
Immune genetic algorithm for scheduling service workflows environment. Concurr. Comput.: Pract. Exp. 25(13), 1816–1842
with QoS constraints in cloud computing. S. Afr. J. Ind. Eng. (2013)
24(3), 68–82 (2013) 313. Alla, H.B., Alla, S.B. and Ezzati, A., 2016, May. A novel
298. Zhao, C., Zhang, S., Liu, Q., Xie, J. and Hu, J., 2009, September. architecture for task scheduling based on dynamic queues and
Independent tasks scheduling based on genetic algorithm in particle swarm optimization in cloud computing. In 2016 2nd
cloud computing. In 2009 5th international conference on International Conference on Cloud Computing Technologies
wireless communications, networking and mobile comput- and Applications (CloudTech) (pp. 108–114). IEEE.
ing (pp. 1–4). IEEE. 314. Askarizade Haghighi, M., Maeen, M., Haghparast, M.: An
299. Almezeini, N., Hafez, A.: Task scheduling in cloud computing energy-efficient dynamic resource management approach based
using lion optimization algorithm. Int. J. Adv. Comput. Sci. on clustering and meta-heuristic algorithms in cloud computing
Appl. (2017). https://doi.org/10.14569/IJACSA.2017.081110 IaaS platforms: energy efficient dynamic cloud resource man-
300. Li, K., Xu, G., Zhao, G., Dong, Y. and Wang, D., 2011, August. agement. Wireless Pers. Commun. 104, 1367–1391 (2019)
Cloud task scheduling based on load balancing ant colony 315. Negi, S., Panwar, N., Vaisla, K.S. and Rauthan, M.M.S., 2020.
optimization. In 2011 sixth annual ChinaGrid conference (pp. Artificial neural network based load balancing in cloud envi-
3–9). IEEE. ronment. In Advances in Data and Information Sciences: Pro-
301. Hu, Y., Xing, L., Zhang, W., Xiao, W. and Tang, D., 2010. A ceedings of ICDIS 2019 (pp. 203–215). Springer Singapore.
knowledge-based ant colony optimization for a grid workflow
scheduling problem. In Advances in Swarm Intelligence: First Publisher’s Note Springer Nature remains neutral with regard to
International Conference, ICSI 2010, Beijing, China, June jurisdictional claims in published maps and institutional affiliations.
12-15, 2010, Proceedings, Part I 1 (pp. 241-248). Springer
Berlin Heidelberg.
Springer Nature or its licensor (e.g. a society or other partner) holds
302. Liu, W., Peng, S., Du, W., Wang, W., Zeng, G.S.: Security-
exclusive rights to this article under a publishing agreement with the
aware intermediate data placement strategy in scientific cloud
author(s) or other rightsholder(s); author self-archiving of the
workflows. Knowl. Inf. Syst. 41, 423–447 (2014)
accepted manuscript version of this article is solely governed by the
303. Javanmardi, S., Shojafar, M., Amendola, D., Cordeschi, N., Liu,
terms of such publishing agreement and applicable law.
H. and Abraham, A., 2014. Hybrid job scheduling algorithm for
cloud computing environment. In Proceedings of the fifth
international conference on innovations in bio-inspired com- Farida Siddiqi Prity completed her Bachelor of Science in
puting and applications IBICA 2014 (pp. 43–52). Springer Information & Communication Engineering in 2020 from Noakhali
International Publishing Science and Technology University, Bangladesh. She is currently
304. Rodriguez, M.A., Buyya, R.: Deadline based resource provi- studying Master of Science in Information & Communication
sioningand scheduling algorithm for scientific workflows on Engineering at the same university. Her research interests are digital
clouds. IEEE Trans. Cloud Comput. 2(2), 222–235 (2014) image processing, cloud computing, Artificial Intelligence, deep
305. Verma, A. and Kaushal, S., 2014, March. Bi-criteria priority learning, transfer learning, and biomedical image processing.
based particle swarm optimization workflow scheduling algo-
rithm for cloud. In 2014 Recent Advances in Engineering and Hasan Gazi has worked as an assistant programmer at the Supreme
Computational Sciences (RAECS) (pp. 1–6). IEEE. Court of Bangladesh. He completed his B.Sc. in Computer Science
306. Milan, S.T., Rajabion, L., Darwesh, A., Hosseinzadeh, M., and Engineering from Patuakhali Science and Technology University,
Navimipour, N.J.: Priority-based task scheduling method over Bangladesh and M.Sc. degree in Computer Science from Jagannath
cloudlet using a swarm intelligence algorithm. Clust. Comput. University, Bangladesh. His research interests are Machine Learning,
23, 663–671 (2020) cloud computing, and image processing.
307. Wang, X., Cao, B., Hou, C., Xiong, L. and Fan, J., 2015,
October. Scheduling budget constrained cloud workflows with Aslam Uddin is currently working as a M.Phil. student under the
particle swarm optimization. In 2015 IEEE Conference on institute of information technology at University of Dhaka, Bangla-
Collaboration and Internet Computing (CIC) (pp. 219–226). desh. Moreover, he is also an Assistant Professor of Information and
IEEE.

123
Cluster Computing

Communication Engineering at Noakhali Science and Technology Science from Jahangirnagar University, Bangladesh. His research
University (NSTU), Noakhali, Bangladesh. He completed his B.Sc. in interest includes cloud computing, machine learning, software
Computer Science and Engineering from Patuakhali Science and engineering.
Technology University, Bangladesh and M.Sc. degree in Computer

123

View publication stats