MEC系统中基于多智能体深度增强学习的协作式任务卸载和资源分配

移动边缘计算(MEC)通过将计算任务卸载到MEC服务器上,在缓解智能移动设备计算负载的同时,可以降低服务时延。然而目前在MEC系统中,关于任务卸载和资源分配仍然存在以下问题：1)边缘节点间缺乏协作;2)计算任务到达与实际环境中动态变化的特征不匹配;3)协作式任务卸载和资源分配动态联合优化问题。为解决上述问题,文章在协作式MEC架构的基础上,提出了一种基于多智能体的深度确定性策略梯度算法(MADDPG)的任务卸载和资源分配算法,最小化系统中所有用户的长期平均成本。仿真结果表明,该算法可以有效降低系统的时延及能耗。     

车联网中基于MEC和任务优先级的智能卸载策略研究

在移动边缘计算和云计算共同组成的车联网中,为了保障驾驶员和路人的安全,需要满足车辆任务的高可靠低时延要求.一种基于MEC和任务优先级的智能卸载策略以降低由时延所组成的系统总成本,该策略使用KNN算法,根据任务优先级对任务卸载位置进行选择.仿真结果表明,该资源分配策略能有效减少系统总成本.     

基于匹配理论的电力物联网边缘服务器选择机制

移动边缘计算利用部署在用户附近基站或具有空闲资源的路侧单元、车辆和MEC服务器作为网络的边缘,为设备提供所需的服务以及云端计算能力,以减少网络操作和服务交付的时延。文章将移动设备和MEC服务器的任务分配问题描述为一对一的匹配博弈,解决了移动边缘计算中的任务卸载问题。文章提出的算法具有良好的扩展性,并且能够降低总体能耗,使任务卸载时延最小化。     

移动边缘计算卸载技术综述

移动边缘计算(Mobile Edge Computing,MEC)将云服务器的计算资源扩展到更靠近用户一侧的网络边缘,使得用户可以将任务卸载到边缘服务器,从而克服原先云计算中将任务卸载到云服务器所带来的高时延问题。首先介绍了移动边缘计算的基本概念、基本框架和应用场景,然后围绕卸载决策、联合资源分配的卸载决策分别从单MEC服务器和多MEC服务器两种场景总结了任务卸载技术的研究现状,最后结合当前MEC卸载技术中存在的不足展望了未来MEC卸载技术的研究。     

基于非正交多址接入的移动边缘计算安全节能联合资源分配

为提高基于非正交多址接入(NOMA)的移动边缘计算(MEC)系统中计算任务部分卸载时的安全性,该文在存在窃听者情况下研究MEC网络的物理层安全,采用保密中断概率来衡量计算卸载的保密性能,考虑发射功率约束、本地任务计算约束和保密中断概率约束,同时引入能耗权重因子以平衡传输能耗和计算能耗,最终实现系统能耗加权和最小。在满足两个用户优先级情况下,为降低系统开销,提出一种联合任务卸载和资源分配机制,通过基于二分搜索的迭代优化算法寻求问题变换后的最优解,并获得最优的任务卸载和功率分配。仿真结果表明,所提算法可有效降低系统能耗。     

移动边缘计算中分布式异构任务卸载算法

随着物联网(IoT)迅速发展,移动边缘计算(MEC)在提供高性能、低延迟计算服务方面的作用日益明显。然而,在面向IoT业务的MEC(MEC-IoT)时变环境中,不同边缘设备和应用业务在时延和能耗等方面具有显著的异构性,对高效的任务卸载及资源分配构成严峻挑战。针对上述问题,该文提出一种动态的分布式异构任务卸载算法(D2HM),该算法利用分布式博弈机制并结合李雅普诺夫优化理论,设计了一种资源的动态报价机制,并实现了对不同业务类型差异化控制和计算资源的弹性按需分配,仿真结果表明,所提的算法可以满足异构任务的多样化计算需求,并在保证网络稳定性的前提下降低系统的平均时延。     

基于移动边缘计算的V2X任务卸载方案

移动边缘计算(MEC)通过在移动网络边缘提供IT服务环境和云计算能力带来高带宽、低时延优势,从而在下一代移动网络的研究中引起了广泛的关注。该文研究车载网络中车辆卸载请求任务时搜寻服务节点为其服务的匹配问题,构建一个基于MEC的卸载框架,任务既可以卸载到MEC服务器以车辆到基础设施(V2I)形式通信,也可以卸载到邻近车辆进行车辆到车辆(V2V)通信。考虑到资源有限性、异构性,任务多样性,建模该框架为组合拍卖模式,提出一种多轮顺序组合拍卖机制,由层次分析法(AHP)排序、任务投标、获胜者决策3个阶段组成。仿真结果表明,所提机制可以在时延和容量约束下,使请求车辆效益提高的同时最大化服务节点的效益。     

移动边缘计算中资源分配和定价方法综述

移动边缘计算（mobile edge computing,MEC）通过将计算任务卸载至边缘服务器，降低网络负荷，减少传输时延，提升用户服务体验。因此，MEC受到了广泛关注，并成为5G的关键技术。资源分配作为MEC的主要问题，在提升能量效率、缩短任务时延和节约成本方面具有非常重大的研究意义。首先，介绍了MEC的基本概念、参考架构和技术优势；然后，从技术层面和经济层面归纳总结了MEC中最新的资源分配和定价策略；最后，讨论了MEC资源分配和定价策略中可能存在的问题与挑战，并提出了一些可行的解决方案，为后续研究发展提供参考。     

一种基于加权K-means的边缘服务器部署方案

随着5G时代的到来,移动边缘计算（MEC）在移动网络的RAN侧提供计算、资源存储和IT服务等系统功能,实现高带宽、低时延的业务支撑和本地管理。从长远角度来看,边缘服务器的合理部署可以提高MEC的服务质量,节省运营商的成本,降低网络资源的浪费。为此,文中提出一种加权K-means算法来优化边缘服务器的部署问题。所提方案根据基站侧的日统计流量计算不同区域范围内移动终端的权值,通过目标方程和约束进行算法设计。在实验阶段,分别通过加权K-means算法、传统K-means算法和随机选择的方法得到边缘服务器的部署位置。在不考虑传输链路异常等情况下,基于不同服务器个数和测试时段,分别计算移动设备与边缘服务器的响应时延。评估结果表明,在相同的移动终端分布和资源分配的条件下,相较于传统K-means算法和随机选择方法,所提方案能够提供更好的部署位置,减少设备的响应时延。     

基于NOMA的超密集MEC网络任务卸载和资源分配方案

为了提高移动边缘计算(mobile edge computing,MEC)网络的频谱效率,满足大量用户的服务需求,建立了基于非正交多址接入(non-orthogonal multiple access,NOMA)的超密集MEC系统模型。为了解决多个用户同时卸载带来的严重通信干扰等问题,以高效利用边缘服务器资源,提出了一种联合任务卸载和资源分配的优化方案,在满足用户服务质量的前提下最小化系统总能耗。该方案联合考虑了卸载决策、功率控制、计算资源和子信道资源分配。仿真结果表明,与其他卸载方案相比,所提方案可以在满足用户服务质量的前提下有效降低系统能耗。     

Deep reinforcement learning-based joint task offloading and bandwidth allocation for multi-user mobile edge computing

The rapid growth of mobile internet services has yielded a variety of computation-intensive applications such as virtual/augmented reality. Mobile Edge Computing (MEC), which enables mobile terminals to offload computation tasks to servers located at the edge of the cellular networks, has been considered as an efficient approach to relieve the heavy computational burdens and realize an efficient computation offloading. Driven by the consequent requirement for proper resource allocations for computation offloading via MEC, in this paper, we propose a Deep-Q Network (DQN) based task offloading and resource allocation algorithm for the MEC. Specifically, we consider a MEC system in which every mobile terminal has multiple tasks offloaded to the edge server and design a joint task offloading decision and bandwidth allocation optimization to minimize the overall offloading cost in terms of energy cost, computation cost, and delay cost. Although the proposed optimization problem is a mixed integer nonlinear programming in nature, we exploit an emerging DQN technique to solve it. Extensive numerical results show that our proposed DQN-based approach can achieve the near-optimal performance.     

V2X offloading and resource allocation under SDN and MEC architecture

To address the serious problem of delay and energy consumption increase and service quality degradation caused by complex network status and huge amounts of computing data in the scenario of vehicle-to-everything (V2X),a vehicular network architecture combining mobile edge computing (MEC) and software defined network (SDN) was constructed.MEC sinks cloud serviced to the edge of the wireless network to compensate for the delay fluctuation caused by remote cloud computing.The SDN controller could sense network information from a global perspective,flexibly schedule resources,and control offload traffic.To further reduce the system overhead,a joint task offloading and resource allocation scheme was proposed.By modeling the MEC-based V2X offloading and resource allocation,the optimal offloading decision,communication and computing resource allocation scheme were derived.Considering the NP-hard attribute of the problem,Agglomerative Clustering was used to select the initial offloading node,and Q-learning was used for resource allocation.The offloading decision was modeled as an exact potential game,and the existence of Nash equilibrium was proved by the potential function structure.The simulation results show that,as compared to other mechanisms,the proposed mechanism can effectively reduce the system overhead.     

Joint partial computation offloading and resource allocation inMEC-enable networks

The sudden surge of various applications poses great challenges to the computation capability of mobile devices. To address this issue, computation offloading to multi-access edge computing(MEC) was proposed as a promising paradigm. This paper studies partial computation offloading scenario by considering time delay and energy consumption, where the task can be splitted into several blocks and computed both in local devices and MEC, respectively. Since the formulated problem is a nonconvex probl...     

Survey on computation offloading in mobile edge computing

Computation offloading in mobile edge computing would transfer the resource intensive computational tasks to the edge network.It can not only solve the shortage of mobile user equipment in resource storage,computation performance and energy efficiency,but also deal with the problem of resource occupation,high latency and network load compared to cloud computing.Firstly the architecture of MEC was introduce and a comparative analysis was made according to various deployment schemes.Then the key technologies of computation offloading was studied from three aspects of decision on computation offloading,allocation of computing resource within MEC and system implement of MEC.Based on the analysis of MEC deployment scheme in 5G,two optimization schemes on computation offloading was proposed in 5G MEC.Finally,the current challenges in the mobility management was summarized,interference management and security of computation offloading in MEC.     

车载边缘计算中任务卸载和服务缓存的联合智能优化

针对车载环境下有限的网络资源和大量用户需求之间的矛盾,提出了智能驱动的车载边缘计算网络架构,以实现网络资源的全面协同和智能管理.基于该架构,设计了任务卸载和服务缓存的联合优化机制,对用户任务卸载以及计算和缓存资源的调度进行了建模.鉴于车载网络的动态、随机和时变的特性,利用异步分布式强化学习算法,给出了最优的卸载决策和资...     

基于二次规划的任务卸载决策和资源分配方法

主要研究移动用户均有多个独立任务的多用户移动云计算系统,这些移动用户将任务卸载到云端时共享通信资源。如何对所有用户的任务卸载决策和通信资源分配进行联合优化,以便使所有用户的能耗、计算量和延时降到最低是目前研究的难点。将该问题建模为NP难度的非凸的具有二次约束的二次规划(QCQP)问题,提出一种高效的近似算法进行求解,通过单独的半正定松驰(SDR)处理后,确定二元卸载决策和通信资源最优分配。采用代表最小系统成本的性能下界作为性能基准进行仿真实验,结果表明,本文算法在多种参数配置下的性能均接近最优性能。     

Task offloading under deterministic demand for vehicular edge computing

In vehicular edge computing (VEC) networks, the rapid expansion of intelligent transportation and the corresponding enormous numbers of tasks bring stringent requirements on timely task offloading. However, many tasks typically appear within a short period rather than arriving simultaneously, which makes it difficult to realize effective and efficient resource scheduling. In addition, some key information about tasks could be learned due to the regular data collection and uploading processes of sensors, which may contribute to developing effective offloading strategies. Thus, in this paper, we propose a model that considers the deterministic demand of multiple tasks. It is possible to generate effective resource reservations or early preparation decisions in offloading strategies if some feature information of the deterministic demand can be obtained in advance. We formulate our scenario as a 0-1 programming problem to minimize the average delay of tasks and transform it into a convex form. Finally, we proposed an efficient optimal offloading algorithm that uses the interior point method. Simulation results demonstrate that the proposed algorithm has great advantages in optimizing offloading utility.     

Multiuser computation offloading for edge-cloud collaboration using submodular optimization

A computation offloading scheme based on edge-cloud computing was proposed to improve the system utility of multiuser computation offloading.This scheme improved the system utility while considering the optimization of edge-cloud resources.In order to tackle the problems of computation offloading mode selection and edge-cloud resource allocation,a greedy algorithm based on submodular theory was developed by fully exploiting the computing and communication resources of cloud and edge.The simulation results demonstrate that the proposed scheme effectively reduces the delay and energy consumption of computing tasks.Additionally,when computing tasks are offloaded to edge and cloud from devices,the proposed scheme still maintains stable system utilities under ultra-limited resources.