Editorial:

Nowadays, a large number of mobile services offer great opportunities of connecting anything at anytime for human beings, e.g., mobile social services, crowdsourcing, crowdsensing, mobile searching, wearable services, mobile robots, etc. However, current mobile services suffer from challenges of high overheads, low quality-of-experience (QoE) and low energy-efficiency. Recent advances of cloud computing, edge computing and artificial intelligence provide a feasible way to address the above concerns and make these mobile services be smarter, more user-friendly but less energy-consuming. With the aid of emerging wireless communications, ubiquitous mobile service providers can interact with each other or even connect to edge/remote cloud computing services via mobile Internet, which potentially establishes a powerful and virtually unlimited computing infrastructure. Thus, heterogeneous cloud-based intelligent computing offers great promises for next-generation mobile services beyond the capabilities of current service providers.

Firstly, mobile service providers employing advanced artificial intelligent techniques, e.g., deep clustering, deep learning, big data analytics, can make intelligent decisions of how to offer proper services to users in an user-friendly way. Such smart services are offered by learning from past experiences with some specific optimized objectives such as minimizing energy consuming and maximizing quality-of-service (QoS)/QoE. However, complex machine learning techniques are generally computation and memory intensive, which is infeasible for a single service provider. On the other hand, heterogeneous cloud integrating cloud, edge and local computing provides unlimited and on-demand computational and memorial resources in a scalable manner. Hence, it is worth combining heterogeneous cloud with intelligent computing to facilitate next-generation mobile services. Secondly, service providers employ a large number of smart devices, e.g., smart sensors, wearable devices and smart phones, to generate a huge volume of mobile data over a short period of time. Accordingly, they utilize heterogeneous cloud-based mobile big data analytics to infer useful information and implicit behavior patterns to further enhance the quality of mobile services. For example, an advertisement recommender would apply big data analytics to analyze mobile big data collected from users, then he/she can determine the preference of target users and make more accurate recommendation. Thirdly, the security of next-generation mobile services is of great concerns by users. Specifically, mobile service providers are required to ensure that their services are secure enough and privacy preserving. Moreover, these services themselves should be secure as well. In other words, service providers should confirm that they provide right services to right users. Hence, learning algorithms, communications, user data and smart devices themselves must be protected seriously at the beginning of mobile service composition.

This special issue features eight selected papers with high quality. The first article, “Software Defined 5G and 6G Networks: A Survey”, authored by Qingyue Long, Yanliang Chen, Haijun Zhang and Xianfu Lei, reviewed the frontier technology of software definition networks (SDN) of 5G and 6G, including system architecture, resource management, mobility management, interference management, challenges, and open issues. The authors introduced a system architectures of 5G and 6G mobile networks based on SDN technologies. Then, they discussed typical SDN-5G/6G application scenarios and key issue. Furthermore, the authors described and compared three types of mobility management mechanism in software defined 5G/6G followed by providing a brief survey of interference management method in SDN-5G/6G. Finally, the authors discussed mm-Wave spectrum, un-availability of popular channel model, massive MIMO, low latency and QoE, energy efficiency, scalability, mobility and routing, inter operability, standardization and security for software defined 5G/6G networks.

The second article titled “An Angle Rotate-QAM Aided Differential Spatial Modulation for 5G Ubiquitous Mobile Networks”, which was authored by Yajun Fan, Liuqing Yang, Dalong Zhang, Gangtao Han and Di Zhang, presented the motivation for enhancing the quality of mobile services supporting the cloud computing services via mobile Internet infrastructure and proposed a high-rate design scheme relying on angle rotate quadrature amplitude modulation (ARQAM) DSM. Specifically, the authors proposed to generate the QAM constellation by exploiting compound phase shift method. Then, the authors investigated the impact of a two-dimensional (2D) regular-shaped geometry-based stochastic model (RS-GBSM) for non-isotropic scattering wideband multiple-input multiple-output vehicle-to-vehicle (V2V) Ricean fading channel based on the proposed ARQAM-aided DSM.

In the next article with the title “Offloading Optimization and Time Allocation for Multiuser Wireless Energy Transfer based Mobile Edge Computing System” authored by Chunlin Lia, Mingyang Songa , Lei Zhang, Weining Chen, Youlong Luo, the authors considered a wireless energy transfer based mobile edge computing system, where wireless devices could be charged by the radio-frequency signals broadcast by hybrid access point. Based on this system, the authors studied the problem of system energy efficiency maximization by joint optimization of computing time allocation, energy consumption, capacity of local computing and task offloading. Then, they proposed a Tabu search based system energy efficiency maximization algorithm to solve the optimization problems.

Directly supporting low-data-rate devices with optimized energy efficiency in the long term evolution advanced (LTE-A) networks is a challenging task. The fourth article entitled “An Energy Efficient Uplink Scheduling and Resource Allocation for M2M Communications in SC-FDMA based LTE-A Networks”, which was authored by Qiyue Li, Yuling Ge, Yangzhao Yang, Yadong Zhu, Wei Sun and Jie Li, investigated the maximum energy efficient data packets M2M transmission with uplink channels in LTE-A networks. The authors formulated it into a joint problem of Modulation-and-Coding Scheme (MCS) assignment, resource allocation and power control, which could be expressed as a non-deterministic polynomial hard (NP-hard) mixed-integer linear fractional programming problem. After that, the authors proposed a global optimization scheme with Charnes-Cooper transformation and Glover linearization.

Non-dominated Sorting Genetic Algorithm II (NSGA-II) is a powerful tool to deal with multi-objective optimization problems (MOPs), and it mainly uses a crowded comparison method (CCM) to select the suitable individuals for enter the next generation. However, the CCM requires to need calculate the crowding distance of each individual, which needs to sort the population according to each objective function and it exhausts a lot of computational burdens. The fifth article, “An Improved Selection Method based on Crowded Comparison for Multi-objective Optimization Problems in Intelligent Computing” authored by Ying Gao, Binjie Song, Hong Zhao, Xiping Hu, Yekui Qian and Xinpeng Chen, proposed an improved crowded comparison method (ICCM), which combined CCM with the random selection method (RSM) based on the number of selected individuals. The RSM was an operator that randomly selected the suitable individuals for the next generation according to the number of needed individuals, which could significantly reduce the computational burdens.

Coal mine wireless sensor network is a typical application scenario of the 5G technology. The sixth article entitled “C-EEUC: a cluster routing protocol for coal mine wireless sensor network based on fog computing and 5G”, which was authored by Wei Chen, Bobin Zhang, Xiao Yang, Weidong Fang, Wuxiong Zhang and Xiaorong Jiang, proposed a centralized non-uniform clustering routing protocol (C-EEUC) based on the residual energy and communication cost. The C-EEUC protocol considered all nodes as candidate cluster heads in the clustering stage and defined a weight matrix. When selecting a cluster head, each time a node with the largest weight was selected from a set of candidate cluster heads followed by updating the candidate cluster head set.

Regarding the research point of accurate flow-awareness through packet sampling, current traffic measurement methods with the five tuples can not recognize the deep information of flows, and the Deep Packet Inspection (DPI) deployed at the gateways or access points is lack of traffic going through the internal nodes. To tackle these challenges, the seventh article, “Improved Flow Awareness among Edge Nodes by Learning-based Sampling in Software Defined Networks” authored by Jun Deng, He Cai, Sheng Chen, Jianji Ren and Xiaofei Wang, presented a flow-level sampling framework for edge devices in the Mobile Edge Computing (MEC) system by means of Deep Q-Network (DQN) and Software-Defined Networking (SDN) technique. Moreover, the authors proposed to effectively collect traffic packets generated from base stations and edge servers in two steps: 1) adaptive node selection, and 2) dynamic sampling duration allocation by Deep Q-Learning.

The last article titled “UAV-based Mobile Wireless Power Transfer Systems with Joint Optimization of User Scheduling and Trajectory”, which was authored by Yi Wang, Meng Hua, Zhi Liu, Di Zhang, Baofeng Ji and Haibo Dai, investigated a mobile wireless power transfer (WPT) system by employing unmanned aerial vehicle (UAV) as mobile energy transmitter (ET) platform, which delivered wireless energy to multiple sensor nodes (SNs) equipped with energy receivers (ERs) on the ground. To optimally explore UAV’s mobility via trajectory design in combination with the proper scheduling stratagem, the authors proposed to jointly optimize the UAV’s trajectory and SNs’ scheduling scheme under UAV’s flying constraints from two different perspectives, i.e. the maximization of sum harvested energy of all SNs and the maximization of the minimum received energy among all SNs.