关键词： Vehicle dynamics   Servers   Computational modeling   Task analysis   Resource management   Markov processes   Edge computing   Virtual reality   mobile edge computing   deep reinforcement learning   Markov decision process   wireless network  

摘要： Virtual reality (VR) is promising to fundamentally transform a broad spectrum of industry sectors and the way humans interact with virtual content. However, despite unprecedented progress, current networking and computing infrastructures are incompetent to unlock VR's full potential. In this paper, we consider delivering the wireless multi-tile VR video service over a mobile edge computing (MEC) network. The primary goal is to minimize the system latency/energy consumption and to arrive at a tradeoff thereof. To this end, we first cast the time-varying view popularity as a model-free Markov chain to effectively capture its dynamic characteristics. After jointly assessing the caching and computing capacities on both the MEC server and the VR playback device, a hybrid policy is then implemented to coordinate the dynamic caching replacement and the deterministic offloading, so as to fully utilize the system resources. The underlying multi-objective problem is reformulated as a partially observable Markov decision process, and a deep deterministic policy gradient algorithm is proposed to iteratively learn its solution, where a long short-term memory neural network is embedded to continuously predict the dynamics of the unobservable popularity. Simulation results demonstrate the superiority of the proposed scheme in achieving a trade-off between the energy efficiency and the latency reduction over the baseline methods.

关键词： Mobile edge computing  

摘要： Mobile edge computing (MEC) deployed cloud computing resources (such as storage and computing power) to the edge of wireless access networks to better meet the development of 5G communication and computing-intensive applications. As the first step of MEC architecture deployment, the placement of the edge server (ES) is the foundation and key, and its location affects the user experience and system performance. In this article, we study the placement of ESs in the heterogeneous networks and express it as an optimization problem. Weighing the response delay and energy consumption as the task overhead, and place the ESs on the optimal access point (AP). An adaptive clustering algorithm MTO based on AP suitability evaluation is proposed to solve the optimal solution, which minimizes the task overhead of computing tasks. Extensive experimental simulations evaluate the performance of the algorithm, and the results show that the MTO algorithm is superior to other representative methods.

关键词： Energy consumption   execution time   mobile edge computing   offloading strategy  

摘要： As mobile devices become more and more powerful, applications generate a large number of computing tasks, and mobile devices themselves cannot meet the needs of users. This article proposes a computation offloading model in which execution units including mobile devices, edge server, and cloud server. Previous studies on joint optimization only considered tasks execution time and the energy consumption of mobile devices, and ignored the energy consumption of edge and cloud server. However, edge server and cloud server energy consumption have a significant impact on the final offloading decision. This paper comprehensively considers execution time and energy consumption of three execution units, and formulates task offloading decision as a single-objective optimization problem. Genetic algorithm with elitism preservation and random strategy is adopted to obtain optimal solution of the problem. At last, simulation experiments show that the proposed computation offloading model has lower fitness value compared with other computation offloading models.

关键词： mobile edge computing   deep reinforcement learning   virtual machine migration  

摘要： Mobile edge computing is a new computing model, which pushes cloud computing power from centralized cloud to network edge. However, with the sinking of computing power, user mobility brings new challenges: since it is usually unstable, services should be dynamically migrated between multiple edge servers to maintain service performance, that is, user-perceived latency. Considering that Mobile Edge Computing is a highly distributed computing environment and it is difficult to synchronize information between servers, in order to ensure the real-time performance of the migration strategy, a virtual machine migration strategy based on Multi-Agent Deep Reinforcement Learning is proposed in this paper. The method of centralized training and distributed execution is adopted, that is, the transfer action is guided by the global information during training, and only the local observation information is needed to obtain the transfer action. Compared with the centralized control method, the proposed method alleviates communication bottleneck. Compared with other distributed control methods, this method only needs local information, does not need communication between servers, and speeds up the perception of the current environment. Migration strategies can be generated faster. Simulation results show that the proposed strategy is better than the contrast strategy in terms of convergence and energy consumption.

关键词： Optimization   Task analysis   Trajectory   Energy consumption   Processor scheduling   Vehicle dynamics   Edge computing   Mobile edge computing   multi-UAVs   two-layer optimization   conflict elimination   decoupling  

摘要： In this study, we introduce a multi-unmanned aerial vehicle (multi-UAV) enabled mobile edge computing (MEC) system, with UAVs as the computing server for the task offloading of ground users. The energy consumption for ground users is minimized by jointly optimizing the UAV task scheduling, bit allocation, and UAV trajectory in a unified framework. To accomplish such goal, we propose a two-layer optimization strategy, where the upper layer optimizes the UAV task scheduling based on a dynamic programming-based bidding optimization method, while the lower one solves the bit allocation and UAV trajectory. In particular, the lower layer is decoupled into several subproblems to reduce the computational complexity, which can be easily solved using an alternating direction method of multipliers. However, the UAV trajectories optimized by solving the decoupled subproblems may lead to path conflicts. As such, we further propose a re-optimization strategy to eliminate such conflicts. Experimental results demonstrate that the proposed strategy achieves a favorable performance than those of greedy and random strategies in terms of total user energy consumption, the trajectory conflicts can be eliminated effectively, and the UAV trajectory can satisfy the safety constraints.

关键词： Mobile edge computing   Computation offloading   Genetic algorithm optimization   Evolutionary optimization   Particle swarm optimization  

摘要： Due to increasing complexity of mobile applications, and limited computation resources of smart mobile devices, the quality of service requirements of mobile application can be enhanced by offloading the computation tasks of the mobile applications to edge servers, such as cloudlets, which exist at the edge of wireless networks. However, improper placement of mobile tasks on the edge servers may increase the waiting time and the transmission time. This, in turn, will increase the response time, and eventually violates the quality of service. This paper proposes an effective offloading strategy in a mobile edge environment using the queuing networks and an evolutionary algorithm, namely the genetic algorithm (GA). The queuing network is used to model the waiting time and the service time of the mobile tasks on the edge servers. The genetic algorithm finds the best allocation of mobile tasks on the edge servers to minimize tasks response time considering the transmission times and the load conditions on edge servers represented by the waiting times and the service times which are calculated using the queuing network. The proposed GA-based offloading algorithm is compared with another evolutionary algorithm, namely particle swarm optimization (PSO). Experimental evaluations show that the GA-based offloading algorithm outperforms both of round robin offloading and the PSO-based offloading algorithms, and effectively improves mobile applications response time. (C) 2021 THE AUTHORS. Published by Elsevier BV on behalf of Faculty of Computers and Artificial Intelligence, Cairo University.

关键词： Multi-access edge computing   Task offloading   Mobile edge computing   Survey  

摘要： With the advent of new technologies in both hardware and software, we are in the need of a new type of application that requires huge computation power and minimal delay. Applications such as face recognition, augmented reality, virtual reality, automated vehicles, industrial IoT, etc. belong to this category. Cloud computing technology is one of the candidates to satisfy the computation requirement of resource-intensive applications running in UEs (User Equipment) as it has ample computational capacity, but the latency requirement for these applications cannot be satisfied by the cloud due to the propagation delay between UEs and the cloud. To solve the latency issues for the delay-sensitive applications a new network paradigm has emerged recently known as Multi-Access Edge Computing (MEC) (also known as mobile edge computing) in which computation can be done at the network edge of UE devices. To execute the resource-intensive tasks of UEs in the MEC servers hosted in the network edge, a UE device has to offload some of the tasks to MEC servers. Few survey papers talk about task offloading in MEC, but most of them do not have in-depth analysis and classification exclusive to MEC task offloading. In this paper, we are providing a comprehensive survey on the task offloading scheme for MEC proposed by many researchers. We will also discuss issues, challenges, and future research direction in the area of task offloading to MEC servers.

关键词： extended training   frame filtering   mobile edge computing   video surveillance  

摘要： The extended training is a global campaign and the video surveillance plays an important role during the process of extended training since it has the considerably requirement on the real-time benefit. The traditional video surveillance system model faces some limitations, such as high resource overhead, serious bandwidth pressure and unwarranted timeliness. Given this, this letter takes full advantages of mobile edge computing to design the video surveillance model, improving the performance of extended training, named MSET. The proposed MSET framework consists of the rich roles, that is, cloud center, wireless base station, edge computing devices and mobile wearables. Driven by the real experiments, the proposed MSET is feasible and outperforms the traditional methods. In particular, the proposed frame filtering algorithm can greatly decrease the process delay.

关键词： Deep reinforcement learning   Computing offloading   Mobile edge computing   Computing resources   Task allocation   offloading decision  

摘要： Aiming at the problems of increased latency and energy consumption and decreased service quality caused by current vehicle networks, this paper proposes a computing offloading resource allocation strategy based on deep reinforcement learning in Internet of Vehicles. Firstly, the system architecture for Internet of Vehicles is designed, calculation model and communication model of computing offloading strategy are constructed. Then, the resource allocation problem in offloading process is studied for real-time energy-aware offloading scheme in mobile edge computing. Besides, considering the battery capacity of vehicle users, the remaining energy rate is utilized to redefine weighting factors to sense energy consumption in real time. Finally, with the shortest delay and smallest computational cost as optimization goals, Q-learning is used to achieve the optimization of offloading strategy, that is, the optimal allocation of communication and computing resources, and the best system security. The simulation results show that the delay of the proposed algorithm is 0.442 s when the computational complexity is 9000 cycles/byte, and the performance of the delay is improved compared with the other three algorithms.

关键词： Collaborative work   Optimization   Computational modeling   Wireless communication   Servers   Quantization (signal)   Resource management   Federated learning   artificial intelligence   mobile edge computing   resource management  

摘要： The combination of artificial intelligence and mobile edge computing (MEC) is considered as a promising evolution path of the future wireless networks. As a model-level coordination learning paradigm, federated learning can make full use of the distributed computation resource in the MEC systems, which allows the users to keep their private data locally. However, due to the unreliable wireless transmission circumstances and resource constraints in the MEC systems, both the performance and training efficiency of federated learning cannot be guaranteed. To solve this problem, the optimization design of federated learning in the MEC systems is studied in this paper. First, an optimization problem is formulated to manage the tradeoff between model accuracy and training cost. Second, a joint optimization algorithm is designed to optimize the model compression, sample selection, and user selection strategies, which can approach a stationary optimal solution in a computationally efficient way. Finally, the performance of our proposed optimization scheme is evaluated by numerical simulation and experiment results, which show that both the accuracy loss and the cost of federated learning in the MEC systems can be reduced significantly by employing our proposed algorithm.