基于边缘计算的新型任务卸载与资源分配策略

针对移动边缘计算（MEC）中密集型任务卸载时，系统开销较大和延时抖动明显的问题，提出一种新型资源分配策略。首先在系统时延约束下，分析了系统任务执行开销与终端设备的资源分配机制；其次建立了基于计算卸载和任务分配的联合凸优化目标；最后采用拉格朗日乘子法进行迭代更新得到最优解。仿真结果表明，所提任务卸载与资源分配方案在保证用户服务质量的同时降低了任务执行开销，并有效提升了MEC系统性能。     

移动边缘计算中基于粒子群优化的计算卸载策略

计算卸载作为移动边缘计算（MEC）中降低时延与能耗的手段之一,通过合理的卸载决策能够降低工业成本。针对工业生产线中部署MEC服务器后时延变长和能耗增高的问题,提出了一种基于粒子群优化（PSO）算法的计算卸载策略PSAO。首先,将实际问题建模为时延模型与能耗模型。由于是针对时延敏感型的应用,因此将模型转化为在能耗约束条件下的最小化时延问题,使用惩罚函数来平衡时延与能耗。其次,根据PSO算法优化后得到计算卸载决策向量,通过集中控制的方式使每一个计算任务合理分配到对应的MEC服务器。最后,通过仿真实验,对比分析了本地卸载策略、MEC基准卸载策略、基于人工鱼群算法（AFSA）的卸载策略以及PSAO的时延数据,PSAO的平均总时延远远低于其他三种卸载策略,PSAO比原来系统总代价降低了20%。实验结果表明,PSAO策略能够降低MEC中的时延,均衡MEC服务器的负载。     

移动边缘计算中利用BPSO的任务卸载策略

为提高移动边缘计算任务卸载方案的性能,提出一种移动边缘计算中利用BPSO的任务卸载策略.构建三层移动边缘计算(M EC)网络架构,移动设备根据任务情况进行本地计算,或者将其卸载至边缘计算节点与云服务器;根据M EC网络中的计算模型、通信模型设计计算卸载目标,即任务最优分配、节点负载均衡,使计算任务得到及时、有序、高效的分配;利用二进制粒子群(BPSO)算法对优化目标进行求解,得到最优卸载策略,实现能量消耗最小且时延最短,系统整体负载最为均衡.实验结果表明,所提策略能量损耗最小且系统整体负载性能明显提升.     

无线供能移动边缘计算系统的安全卸载优化

针对能量受限的多用户移动边缘计算（MEC）系统存在恶意窃听节点的问题,提出一种联合无线能量传输（WPT）和MEC的安全部分计算卸载方案。该方法以系统接入点（AP）能耗最小化为优化目标,在计算延迟、安全卸载和能量捕获约束条件下,联合优化AP能量传输协方差矩阵、本地CPU频率、用户卸载比特数、用户卸载时间分配以及用户传输功率。针对AP能耗最小化问题为非凸问题,首先采用凸差分算法（DCA）将原始非凸问题转换为凸问题,然后采用拉格朗日对偶法以半封闭形式获得问题最优解。当计算任务数为5×10⁵比特时,与本地计算和安全全部计算卸载方法相比,安全部分卸载方案的能量消耗分别降低了61.3%和84.4%;当窃听节点距离超过25 m时,安全部分卸载方案所消耗的能量远小于本地计算和安全全部计算卸载。仿真实验结果表明,在保证物理层安全卸载的情况下,所提方案能够有效降低AP能耗、提高系统性能增益。     

移动边缘计算中一种贪心策略的内容卸载方案

基于移动边缘计算的内容卸载技术可以有效降低骨干网络的流量压力,提升终端用户体验。针对终端用户与小基站之间的异质接触率,设计了一种贪心策略的内容卸载方案。首先,将内容最优卸载问题转化为内容最大投递率问题;其次,证明最大投递率问题满足子模性,在此基础上,采用贪心算法部署内容,该算法可以以概率（1-1/e）保证其最优性;最后,详细分析了内容流行度指数以及缓存大小对不同卸载方案的影响。实验结果表明,所提方案提高了内容投递率同时降低了内容传输时延。     

移动边缘计算中基于改进拍卖模型的计算卸载策略

随着移动互联网业务的快速发展,增强现实、虚拟现实、超清视频等手机应用逐渐普及、IoT应用不断涌现,计算能力和续航能力的不足成为限制智能终端设备成功支撑这些应用的主要瓶颈。针对这一现状,采用计算卸载的方式解决该问题,在多用户多移动边缘服务器的场景下,综合考虑智能设备性能和服务器资源提出了一种基于改进拍卖算法的计算卸载策略。该策略主要包括两个阶段,在卸载决策阶段,通过综合考虑计算任务自身大小、计算需求和服务器计算能力、网络带宽等因素提出了卸载决策的依据;在任务调度阶段,通过综合考虑计算任务的时间需求和MEC服务器计算性能提出了基于改进拍卖算法的任务调度模型。实验证明,提出的计算卸载策略能够有效地降低服务时延,减少智能设备能耗,改善用户体验。     

DBAHHO: Deep belief network-based adaptive Harris Hawks optimization for adaptive offloading strategy in mobile edge computing

The Journal of Supercomputing - Mobile edge computing (MEC) is an emerging paradigm that decreases the computational burden of mobiles by task offloading. MEC is regarded as an effective method to...     

CoTask: Correlation-aware task offloading in edge computing

World Wide Web - In this paper, we first study the problem of Correlation-aware Task computation offloading (CoTask) in mobile edge computing. Specifically, considering the correlation among...     

Computation offloading and service allocation in mobile edge computing

The Journal of Supercomputing - The intensive mobile data traffic poses a great challenge for energy-constrained mobile devices. In the mobile edge environment, effective computing offloading and...     

考虑任务依赖的卫星边缘计算资源分配与卸载决策算法

针对高低轨卫星网络协同边缘计算的卸载决策问题,提出了一种考虑任务依赖的联合计算资源、无线资源分配与任务调度的卫星网络边缘计算卸载决策算法。首先,将任务卸载问题建模为最小化任务延迟和能量消耗的联合优化问题;然后,将能源消耗和时延引入子任务优先级定义中,基于动态优先级进行启发式卸载策略搜索。该算法保证了子任务之间的依赖性并同时考虑了无线资源分配。仿真结果表明,与已有研究相比,该算法能缩短高低轨卫星协同计算的任务执行延迟,且能够降低低轨卫星功耗。     

移动边缘环境下面向工作流管理的计算迁移方法

针对移动边缘环境下移动设备大量的能源消耗问题，为了优化移动设备的能源消耗，提出一种能耗感知的工作流计算迁移（EOW）方法。首先，基于排队论分析边缘设备中计算任务的平均等待时间，建立了移动设备的时间模型和能耗模型；然后，基于非支配排序算法（NSGA-Ⅲ）提出对应的计算迁移方法，对工作流的计算任务进行合理的分配，将一部分计算任务留在移动设备处理，或者迁移到边缘计算平台和远程云端，实现每个移动设备的节能目标；最后，通过CloudSim仿真平台对提出的计算迁移方法进行仿真和对比实验。实验结果表明，EOW方法能够明显地减少每个移动设备的能源消耗，同时满足每一个工作流的截止时间的要求。     

移动边缘计算中基于深度强化学习的计算卸载调度方法

针对移动边缘计算中具有依赖关系的任务的卸载决策问题,提出一种基于深度强化学习的任务卸载调度方法,以最小化应用程序的执行时间。任务调度的过程被描述为一个马尔可夫决策过程,其调度策略由所提出的序列到序列深度神经网络表示,并通过近端策略优化(proximal policy optimization)方法进行训练。仿真实验表明,所提出的算法具有良好的收敛能力,并且在不同环境下的表现均优于所对比的六个基线算法,证明了该方法的有效性和可靠性。     

Optimal sequential relay-remote selection and computation offloading in mobile edge computing

The Journal of Supercomputing - In this paper, we investigate a MEC relay-assisted system with multiple relay nodes (RNs) and multiple remote servers (RSs), where both the selections of best RN and...     

Multi-device task offloading with time-constraints for energy efficiency in mobile cloud computing

Nowadays, in order to deal with the increasingly complex applications on mobile devices, mobile cloud offloading techniques have been studied extensively to meet the ever-increasing energy requirements. In this study, an offloading decision method is investigated to minimize the energy consumption of mobile device with an acceptable time delay and communication quality. In general, mobile devices can execute a sequence of tasks in parallel. In the proposed offloading decision method, only parts of the tasks are offloaded for task characteristics to save the energy of multi-devices. The issue of the offloading decision is formulated as an NP-hard 0–1 nonlinear integer programming problem with time deadline and transmission error rate constraints. Through decision-variable relaxation from the integer to the real domain, this problem can be transformed as a continuous convex optimization. Based on Lagrange duality and the Karush–Kuhn–Tucker condition, a solution with coupled terms is derived to determine the priority of tasks for offloading. Then, an iterative decoupling algorithm with high efficiency is proposed to obtain near-optimal offloading decisions for energy saving. Simulation results demonstrate that considerable energy can be saved via the proposed method in various mobile cloud scenarios.     

Resource pricing and offloading decisions in mobile edge computing based on the Stackelberg game

We propose a new approach for the organic integration of edge cloud offloading decision and Stackelberg game pricing to address the problem that the current Stackelberg games all allocate edge cloud computing resources equally and ignore the difference of different users’ demand for computing resources. Firstly, the Stackelberg game theory is used to establish a model of the optimal amount of data to be offloaded by users and the optimal number of computing resource blocks to be purchased, which converts the multivariate offloading decision problem of users into a univariate optimization problem, simplifies the offloading decision problem of users, and proves the existence of Nash equilibrium. Secondly, the KKT condition is applied to realize the offloading decision of users to purchase the optimal computing resource blocks. The upper and lower bounds of edge cloud pricing are established. Finally, a dynamic programming-based offloading (DPPO) algorithm for edge cloud pricing is proposed to achieve the optimal pricing of edge cloud utility and maximize each user’s own utility. The simulation results show that the proposed method not only achieves the equilibrium of edge cloud utility and user utility, but also has good convergence and scalability. The DPPO algorithm yields better results than with different pricing and offloading strategies.

     

移动边缘计算环境中面向机器学习的计算迁移策略

针对物联网(IoT)数据源的多样化、数据的非独立同分布性、边缘设备计算能力和能耗的异构性,提出一种集中学习和联邦学习共存的移动边缘计算(MEC)网络计算迁移策略.首先,建立与集中学习、联邦学习都关联的计算迁移系统模型,考虑了集中学习、联邦学习模型产生的网络传输延迟、计算延迟以及能耗;然后,以系统平均延迟为优化目标、以能...     

移动云计算中的任务调度与计算迁移算法

随着互联网的发展,许多应用程序对计算机的计算能力和资源的需求越来越大,而移动设备具有有限的资源和计算能力,云计算迁移技术是解决计算密集型任务在移动端上顺利运行的主流方法。针对无线网络中联合调度和迁移的问题,提出了一个快速高效的启发式算法。算法将能够迁移的任务全部迁移到云端作为初始解,然后逐次计算可迁移任务在移动端运行的能耗节省量,依次将节省量最大的任务迁移到移动端。每迁移一个任务,该算法都会依据任务间的通信时间,及时更新各个任务的能耗节省量。为了进一步优化启发式算法得到的解,还构造了适用于此问题并以启发解为初始解的模拟退火算法,给出了相应的编码方法、目标函数、邻域解、温度参数以及算法终止准则。与无迁移、饱和迁移、随机迁移三类算法的对比实验结果表明,由启发式算法得出的解具有高效性,能给出使移动端能耗更小的解。     

基于最小完成时间的车载边缘计算任务流卸载策略

为在具有不稳定网络拓扑结构的车载边缘环境下实现车载任务的顺利卸载,提出一种基于动态优先级的最早完成时间卸载策略.根据车辆的速度、位置以及周围资源的使用状态等多种实时的信息筛选出可用卸载资源,以任务自身属性与可用资源的实际匹配程度作为基础为任务选择合适的卸载策略,实现任务流的完成时间最小化.实验结果表明,与其它策略相比,提出策略可以有效降低任务流的完成时间.     

A review on the computation offloading approaches in mobile edge computing: A game-theoretic perspective

In recent years, novel mobile applications such as augmented reality, virtual reality, and three-dimensional gaming, running on handy mobile devices have been pervasively popular. With rapid developments of such mobile applications, decentralized mobile edge computing (MEC) as an emerging distributed computing paradigm is developed for serving them near the smart devices, usually in one hop, to meet their computation, and delay requirements. In the literature, offloading mechanisms are designed to execute such mobile applications in the MEC environments through transferring resource-intensive tasks to the MEC servers. On the other hand, due to the resource limitations, resource heterogeneity, dynamic nature, and unpredictable behavior of MEC environments, it is necessary to consider the computation offloading issues as the challenging problem in the MEC environment. However, to the best of our knowledge, despite its importance, there is not any systematic, comprehensive, and detailed survey in game theory (GT)-based computation offloading mechanisms in the MEC environment. In this article, we provide a systematic literature review on the GT-based computation offloading approaches in the MEC environment in the form of a classical taxonomy to recognize the state-of-the-art mechanisms on this important topic and to provide open issues as well. The proposed taxonomy is classified into four main fields: classical game mechanisms, auction theory, evolutionary game mechanisms, and hybrid-base game mechanisms. Next, these classes are compared with each other according to the important factors such as performance metrics, case studies, utilized techniques, and evaluation tools, and their advantages and disadvantages are discussed, as well. Finally, open issues and future uncovered or weakly covered research challenges are discussed and the survey is concluded.