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： 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： Wireless communication   Body area networks   Servers   Task analysis   Medical services   Energy consumption   Games   Mobile edge computing   WBAN   green MEC   task offloading   incentive   5G healthcare  

摘要： With the unprecedented growth of wireless body area network (WBAN) users and computation-intensive 5G-based healthcare applications, mobile edge computing (MEC)-enabled healthcare systems that enable computation offloading to edge servers in proximity, are gaining much interest. However, due to the ever-increasing requirement of WBAN users' quality of experience (QoE), the computational load on the MEC server increases, resulting in high energy costs and heavy carbon emissions. Therefore, in this paper, we focus on joint cost and energy-efficient task offloading in the MEC-enabled healthcare system by designing incentives for WBAN users to curtail their amount of task offloading. In particular, we model the interaction among the MEC server and WBAN users using the Stackelberg game and derive the optimal task offloading decision for WBAN users and corresponding reimbursement amount. As the number of WBAN users is large, we propose an alternating direction method of multipliers (ADMM)-based algorithm to achieve the optimal solution in a distributed manner. Further, simulation results show that the proposed algorithm maximizes the payoffs of both the MEC server and the WBAN users, while also reducing the MEC server energy cost by 52.38% compared to benchmark schemes.

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： Task analysis   Servers   Internet of Things   Solid modeling   Computational modeling   Energy consumption   Reinforcement learning   Mobile edge computing   deep reinforcement learning   computation offloading   latency   energy efficiency  

摘要： Internet of Things (IoT) is considered as the enabling platform for a variety of promising applications, such as smart transportation and smart city, where massive devices are interconnected for data collection and processing. These IoT applications pose a high demand on storage and computing capacity, while the IoT devices are usually resource constrained. As a potential solution, mobile edge computing (MEC) deploys cloud resources in the proximity of IoT devices so that their requests can be better served locally. In this work, we investigate computation offloading in a dynamic MEC system with multiple edge servers, where computational tasks with various requirements are dynamically generated by IoT devices and offloaded to MEC servers in a time-varying operating environment (e.g., channel condition changes over time). The objective of this work is to maximize the completed tasks before their respective deadlines and minimize energy consumption. To this end, we propose an end-to-end Deep Reinforcement Learning (DRL) approach to select the best edge server for offloading and allocate the optimal computational resource such that the expected long-term utility is maximized. The simulation results are provided to demonstrate that the proposed approach outperforms the existing 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： 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.

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： hierarchical strategy   mobile edge computing   task scheduling  

摘要： Mobile Edge Computing (MEC) has attracted much attention from the global researchers because it supports the task migration from the cloud server to the mobile edge devices, which greatly improves the computation performance. Under MEC, this letter proposes a hierarchical task scheduling strategy. To be specific, the system framework includes the edge computing layer and the frog computing layer, in which the former is responsible for processing the simple tasks (outputting the sketchy result) and the latter is used to addressing the complex tasks (outputting the precise result). In particular, the tasks after going through the edge computing layer, they are allocated with the priorities;on this basis, the frog computing layer embeds a priority-based task scheduling strategy. The experimental results demonstrate that the proposed hierarchical scheduling strategy not only is feasible but also has better delay performance and load balance performance than the benchmarks.