关键词： Mobile edge computing   Container migration   Multi-user mobility   Deep reinforcement learning   Aware delay   Energy consumption  

摘要： Recently, mobile edge computing(MEC) has attracted considerable research effort, because mobile users can offload some tasks to edge servers that are closer to users than cloud servers for a better computing experience, which can bring enormous potential in next-generation wireless networks(5G). However, when users are moving, they may be far away from the edge server that undertakes the offloading task, resulting in unavoidable service discontinuity and degrading the user experience. Service migration mechanism is very crucial in 5G mobile Internet. In this paper, we propose a novel service migration scheme to support mobility. Our scheme is realized from three aspects: (1) we consider mobile user services can be deployed container virtual machine in corresponding edge servers, and develop container migration strategies to satisfy the trade-off between the users' aware delay and system energy consumption;(2) we further propose a deep reinforcement learning algorithm (DRL) based such multi-user server migration strategy (DRLMSM) to effectively achieve fast decision-making;(3) we build the architecture in Software Defined Network (SDN) framework to verify the practicality and effectiveness of DRLMSM. We conduct extensive experiments, which shows that our DRLMSM scheme outperforms the classical reinforcement learning(RL) algorithm and some other baseline algorithm. (C) 2021 Elsevier B.V. All rights reserved.

关键词： Trust and verifiable   Ultra-reliable applications   Baseline data   5G and beyond networks   Mobile edge computing  

摘要： With the development of Internet of Thing (IoT) joint 5G and Beyond Networks, Mobile Edge Users (MEUs) can act as mobile data collectors to collect data for various applications. However, some malicious MEUs reporting false or malicious data can cause serious harm to applications, especially for ultra-reliable applications. A novel Verifiable Trust Evaluation joint UAV (VTE-UAV) mechanism is proposed to select trustworthy MEUs to conduct the task for ultra-reliable applications. The VTE-UAV strategy adopts two novel trust evaluation methods, one is the aggregation-based MEU trust evaluation mechanism, when malicious evaluation objects are in the minority, the mechanism takes most evaluation results as baseline data. The other is an active trust acquisition mechanism, it takes the data obtained by Unmanned Aerial Vehicles (UAVs) as baseline data to actively validate the authenticity of the data. Through these two cross evaluation strategies, we obtain more accurate trust evaluation results. Finally, this paper transforms the trust evaluation optimization problem into the optimization of the accuracy of trust evaluation with reducing the cloud payment and the dispatch cost of UAVs. Extensive experiments have verified the validity of the VTE-UAV strategy. Compared with the previous strategies, the VTE-UAV improves the cloud recruitment performance by 7.74%-25.91%, increases the accuracy of trust evaluation of IoT devices by 2.24%-11.72%, and reduces the cloud payment and the cost of UAVs by 3.11%-10.20% and 58.23%, respectively.

关键词： Device-to-device communication   Relays   Cloud computing   Processor scheduling   Wireless communication   Uplink   Dynamic scheduling   Mobile edge computing   D2D communication   partial offloading   cooperative scheduling   computation allocating  

摘要： By fully exploiting the cooperative communication capacities among mobile terminals (MTs), the MTs can adapt the offloading designs well to the practical network with dynamic features. In this paper, joint multi-user cooperative partial offloading, transmission scheduling and computation allocating is discussed for device-to-device (D2D) underlay mobile edge computing (MEC). By considering stochastic application requests, unpredictable MTs states, time-varying channel states and computation resources, a customized application offloading model, which aims to minimize the network-wide response latency and energy consumption simultaneously, is formulated. In order to solve this non-convex and non-smooth optimization problem, an online resource coordinating and allocating scheme (ORCAS) is proposed by exploiting Lyapunov optimization theory, variable substitution technique and resource provisioning priority mechanism. Both theoretical analyses and simulation results demonstrate that the proposed ORCAS can 1) drive the application response cost converge to the minimum;2) achieve superior performance (e.g., the average network-wide response cost under ORCAS is approximately 19.14% lower than that under partial offloading directly);3) adapt to dynamic situations in terms of stochastic user demands and channel states.

关键词： Deep reinforcement learning   green energy   heterogeneous service   mobile edge computing   power consumption   resource allocation  

摘要： The requirements for powerful computing capability, high capacity, low latency and low energy consumption of emerging services, pose severe challenges to the fifth-generation (5G) network. As a promising paradigm, mobile edge networks can provide services in proximity to users by deploying computing components and cache at the edge, which can effectively decrease service delay. However, the coexistence of heterogeneous services and the sharing of limited resources lead to the competition between various services for multiple resources. This paper considers two typical heterogeneous services: computing services and content delivery services, in order to properly configure resources, it is crucial to develop an effective offloading and caching strategies. Considering the high energy consumption of 5G base stations, this paper considers the hybrid energy supply model of traditional power grid and green energy. Therefore, it is necessary to design a reasonable association mechanism which can allocate more service load to base stations rich in green energy to improve the utilization of green energy. This paper formed the joint optimization problem of computing offloading, caching and resource allocation for heterogeneous services with the objective of minimizing the on-grid power consumption under the constraints of limited resources and QoS guarantee. Since the joint optimization problem is a mixed integer nonlinear programming problem that is impossible to solve, this paper uses deep reinforcement learning method to learn the optimal strategy through a lot of training. Extensive simulation experiments show that compared with other schemes, the proposed scheme can allocate resources to heterogeneous service according to the green energy distribution which can effectively reduce the traditional energy consumption.

关键词： Mobile edge computing  

摘要： Nowadays, Internet of Video Things (IoVT) grows rapidly in terms of quantity and computation demands. In spite of the higher local computation capability on visual processing compared with conventional Internet of Things devices, IoVT devices need to offload partial visual processing tasks to the mobile edge computing (MEC) server wirelessly due to its larger computation demands. However, visual processing task offloading is limited by uplink throughput and computation capability of the MEC server. To break through these limitations, a novel non-orthogonal multiple access (NOMA) assisted IoVT framework with multiple MEC servers is proposed, where NOMA is exploited to improve uplink throughput and MEC servers are co-located with base stations to provide enough computation capability for offloading. In the proposed framework, the association strategy, uplink visual data transmission assisted by NOMA and division of the visual processing tasks as well as computation resource allocation at the MEC servers are jointly optimized to minimize the total delay of all visual processing tasks, while meeting the delay requirements of all IoVT devices. Simulation results demonstrate that significant performance gains can be achieved by proposed joint optimization with NOMA transmission and multi-MEC offloading in the heterogeneous IoVT network. © 2021, CC BY.

关键词： Mobile edge computing   Task offloading   Particle swarm optimization   Industrial internet of things  

摘要： As a new form of computing based on the core technology of cloud computing and built on edge infrastructure, edge computing can handle computing-intensive and delay-sensitive tasks. In mobile edge computing (MEC) assisted by 5G technology, offloading computing tasks of edge devices to the edge servers in edge network can effectively reduce delay. Designing a reasonable task offloading strategy in a resource-constrained multi-user and multi-MEC system to meet users' needs is a challenge issue. In industrial internet of things (IIoT) environment, considering the rapid increase of industrial edge devices and the heterogenous edge servers, a particle swarm optimization (PSO)-based task offloading strategy is proposed to offload tasks from resource-constrained edge devices to edge servers with energy efficiency and low delay style. A multi-objective optimization problem that considers time delay, energy consumption and task execution cost is proposed. The fitness function of the particle represents the total cost of offloading all tasks to different MEC servers. The offloading strategy based on PSO is compared with the genetic algorithm (GA) and the simulated annealing algorithm (SA) through simulation experiments. The experimental results show that the task offloading strategy based on PSO can reduce the delay of the MEC server, balance the energy consumption of the MEC server, and effectively realize the reasonable resource allocation.

关键词： Autonomous driving   Computing resource scheduling   Mobile edge computing   Vehicle-infrastructure cooperation  

摘要： Purpose With the continuous technological development of automated driving and expansion of its application scope, the types of on-board equipment continue to be enriched and the computing capabilities of on-board equipment continue to increase and corresponding applications become more diverse. As the applications need to run on on-board equipment, the requirements for the computing capabilities of on-board equipment become higher. Mobile edge computing is one of the effective methods to solve practical application problems in automated driving. Design/methodology/approach In this study, in accordance with practical requirements, this paper proposed an optimal resource management allocation method of autonomous-vehicle-infrastructure cooperation in a mobile edge computing environment and conducted an experiment in practical application. Findings The design of the road-side unit module and its corresponding real-time operating system task coordination in edge computing are proposed in the study, as well as the method for edge computing load integration and heterogeneous computing. Then, the real-time scheduling of highly concurrent computation tasks, adaptive computation task migration method and edge server collaborative resource allocation method is proposed. Test results indicate that the method proposed in this study can greatly reduce the task computing delay, and the power consumption generally increases with the increase of task size and task complexity. Originality/value The results showed that the proposed method can achieve lower power consumption and lower computational overhead while ensuring the quality of service for users, indicating a great application prospect of the method.

关键词： Mobile edge computing  

摘要： This paper studies a problem of jointly optimizing two important operations in mobile edge computing without knowing future requests, namely service caching, which determines which services to be hosted at the edge, and service routing, which determines which requests to be processed locally at the edge. We aim to address several practical challenges, including limited storage and computation capacities of edge servers and unknown future request arrival patterns. To this end, we formulate the problem as an online optimization problem, in which the objective function includes costs of forwarding requests, processing requests, and reconfiguring edge servers. By leveraging a natural timescale separation between service routing and service caching, namely, the former happens faster than the latter, we propose an online two-stage algorithm and its randomized variant. Both algorithms have low complexity, and our fractional solution achieves sublinear regret. Simulation results show that our algorithms significantly outperform other state-of-the-art online policies. Copyright © 2021, The Authors. All rights reserved.

关键词： Mobile edge computing  

摘要： Multi-Agent Reinforcement Learning (MARL) is a challenging subarea of Reinforcement Learning due to the non-stationarity of the environments and the large dimensionality of the combined action space. Deep MARL algorithms have been applied to solve different task offloading problems. However, in real-world applications, information required by the agents (i.e. rewards and states) are subject to noise and alterations. The stability and the robustness of deep MARL to practical challenges is still an open research problem. In this work, we apply state-of-the art MARL algorithms to solve task offloading with reward uncertainty. We show that perturbations in the reward signal can induce decrease in the performance compared to learning with perfect rewards. We expect this paper to stimulate more research in studying and addressing the practical challenges of deploying deep MARL solutions in wireless communications systems. © 2021, CC0.

关键词： Mobile edge computing  

摘要： In this paper, we consider a system model in conjunction with two major technologies in 5G communications, i.e., mobile edge computing and spectrum sharing. An IoT network, which does not have access to any licensed spectrum, carries its computational task offloading activities with help of spectrum sharing. The IoT network cooperates with a licensed spectrum holding network by relaying its data and in return gets access to the licensed spectrum. The licensed spectrum holding network focuses on throughput maximization, whereas, the IoT network tries to maximize task computation rate. We formulate an optimization problem giving importance to both networks’ interests. Typical IoT nodes may be energy-constrained, which is considered along with task computation time constraints. Parallel computation is considered while computing IoT nodes’ computational tasks at the mobile edge computing server, where the processor is allocated based on IoT nodes’ offloading capabilities. The advantage of such processor allocation is shown in the result section. Moreover, we also show how both IoT and licensed spectrum holding networks benefit from the spectrum sharing by caring for each other requirements, which echoes the fact, i.e., Sharing is Caring. © 2021, CC BY-NC-SA.