Modern society is impossible without the digital economy, which increasingly provides a significa... more Modern society is impossible without the digital economy, which increasingly provides a significant amount of services, guaranteeing technological efficiency and innovation, constantly updating technologies and services, adapting them to the needs of the end user, reconfiguring complex software systems. All of this requires constant workflows reengineering in subject areas, and, accordingly, an increase in the level of their automation. At the same time, there are currently no efficient solutions for automated workflows reengineering. This article presents an approach to the computational workflows construction, which is based on well-defined ontological models of the domain, an ontological model of a set of rules for building connections between functional services, and an ontological model of the workflows themselves that are dynamically generated. The research of this approach has been carried out and the prototype for the automated computational workflows construction has been d...
Global digital transformation requires more productive large scale distributed systems. Such syst... more Global digital transformation requires more productive large scale distributed systems. Such systems should meet lots of requirements, such as high availability, low latency, reliability. However, new challenges become more and more important nowadays. One of them is energy efficiency of large scale computing systems. Many service providers prefer to use cheap commodity servers in their distributed infrastructure, what makes the problem of energy efficiency even harder because of hardware inhomogeneity. In this chapter an approach to finding balance between performance and energy efficiency requirements within inhomogeneous distributed computing environment is proposed. The main idea of the proposed approach is to use each node’s individual energy consumption models in order to generate distributed system scaling patterns based on the statistical daily workload, and then adjust these patterns to match the current workload, while using PCPB scheduling strategy to optimize hardware utilization. An approach is tested using Matlab modelling. As a result of applying the proposed approach, large-scale distributed computing systems save energy while maintaining a fairly high level of performance and meeting the requirements of the service level agreement (SLA).
Network function virtualization is considered as an important shift in the telecommunications and... more Network function virtualization is considered as an important shift in the telecommunications and has received huge attention recently. However, efficiently running virtualized services is not trivial, as, among other initialization steps, it requires mapping virtual networks on physical networks. The paper addresses the mobile network virtualization. The objective of the study is to improve the efficiency of mobile networks through optimal resource allocation in hybrid data center environment. In this direction, the paper proposes an approach to model and investigate the dynamic allocation of network functions on a telecommunication operator's network. The method can be used in the management of deployment of network functions in heterogeneous hardware environment in order to minimize operator costs and maintain the required quality of experience.
Application of Data Mining Methods in Telecommunication Systems Currently, there is an intensive ... more Application of Data Mining Methods in Telecommunication Systems Currently, there is an intensive development of telecommunication systems, accompanied by tough competition for the client. Data analysis aimed at identifying hidden patterns is implemented using the methods of modern information technology Data Mining.
Energy efficiency, performance and service availability are the key performance indicators of mod... more Energy efficiency, performance and service availability are the key performance indicators of modern Smart Networks. These networks use large-scale distributed computing systems to provide high-performance data processing. In such systems, it is always difficult to find a balance between performance and power consumption, given the possible heterogeneity of nodes in a distributed system. Existing approaches propose using horizontal scaling, workload consolidation, and energy-efficient scheduling to improve the energy efficiency of large-scale distributed systems while maintaining sufficient processing performance. We propose to combine the benefits of horizontal scaling and energy efficient scheduling and model the system as a queuing system to achieve the optimal balance of performance, power consumption, and service availability in our PCPB-2 approach. Experimental analysis of the approach proves its efficiency up to 8.9% compared to the state-of-the-art Backfill energy-aware scheduling approach.
Modern society is impossible without the digital economy, which increasingly provides a significa... more Modern society is impossible without the digital economy, which increasingly provides a significant amount of services, guaranteeing technological efficiency and innovation, constantly updating technologies and services, adapting them to the needs of the end user, reconfiguring complex software systems. All of this requires constant workflows reengineering in subject areas, and, accordingly, an increase in the level of their automation. At the same time, there are currently no efficient solutions for automated workflows reengineering. This article presents an approach to the computational workflows construction, which is based on well-defined ontological models of the domain, an ontological model of a set of rules for building connections between functional services, and an ontological model of the workflows themselves that are dynamically generated. The research of this approach has been carried out and the prototype for the automated computational workflows construction has been d...
Global digital transformation requires more productive large scale distributed systems. Such syst... more Global digital transformation requires more productive large scale distributed systems. Such systems should meet lots of requirements, such as high availability, low latency, reliability. However, new challenges become more and more important nowadays. One of them is energy efficiency of large scale computing systems. Many service providers prefer to use cheap commodity servers in their distributed infrastructure, what makes the problem of energy efficiency even harder because of hardware inhomogeneity. In this chapter an approach to finding balance between performance and energy efficiency requirements within inhomogeneous distributed computing environment is proposed. The main idea of the proposed approach is to use each node’s individual energy consumption models in order to generate distributed system scaling patterns based on the statistical daily workload, and then adjust these patterns to match the current workload, while using PCPB scheduling strategy to optimize hardware utilization. An approach is tested using Matlab modelling. As a result of applying the proposed approach, large-scale distributed computing systems save energy while maintaining a fairly high level of performance and meeting the requirements of the service level agreement (SLA).
Network function virtualization is considered as an important shift in the telecommunications and... more Network function virtualization is considered as an important shift in the telecommunications and has received huge attention recently. However, efficiently running virtualized services is not trivial, as, among other initialization steps, it requires mapping virtual networks on physical networks. The paper addresses the mobile network virtualization. The objective of the study is to improve the efficiency of mobile networks through optimal resource allocation in hybrid data center environment. In this direction, the paper proposes an approach to model and investigate the dynamic allocation of network functions on a telecommunication operator's network. The method can be used in the management of deployment of network functions in heterogeneous hardware environment in order to minimize operator costs and maintain the required quality of experience.
Application of Data Mining Methods in Telecommunication Systems Currently, there is an intensive ... more Application of Data Mining Methods in Telecommunication Systems Currently, there is an intensive development of telecommunication systems, accompanied by tough competition for the client. Data analysis aimed at identifying hidden patterns is implemented using the methods of modern information technology Data Mining.
Energy efficiency, performance and service availability are the key performance indicators of mod... more Energy efficiency, performance and service availability are the key performance indicators of modern Smart Networks. These networks use large-scale distributed computing systems to provide high-performance data processing. In such systems, it is always difficult to find a balance between performance and power consumption, given the possible heterogeneity of nodes in a distributed system. Existing approaches propose using horizontal scaling, workload consolidation, and energy-efficient scheduling to improve the energy efficiency of large-scale distributed systems while maintaining sufficient processing performance. We propose to combine the benefits of horizontal scaling and energy efficient scheduling and model the system as a queuing system to achieve the optimal balance of performance, power consumption, and service availability in our PCPB-2 approach. Experimental analysis of the approach proves its efficiency up to 8.9% compared to the state-of-the-art Backfill energy-aware scheduling approach.
Uploads
Papers by Larysa Globa