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...     

Joint computation offloading and task caching for multi-user and multi-task MEC systems: reinforcement learning-based algorithms

Computation offloading at mobile edge computing (MEC) servers can mitigate the resource limitation and reduce the communication latency for mobile devices. Thereby, in this study, we proposed an offloading model for a multi-user MEC system with multi-task. In addition, a new caching concept is introduced for the computation tasks, where the application program and related code for the completed tasks are cached at the edge server. Furthermore, an efficient model of task offloading and caching integration is formulated as a nonlinear problem whose goal is to reduce the total overhead of time and energy. However, solving these types of problems is computationally prohibitive, especially for large-scale of mobile users. Thus, an equivalent form of reinforcement learning is created where the state spaces are defined based on all possible solutions and the actions are defined on the basis of movement between the different states. Afterwards, two effective Q-learning and Deep-Q-Network-based algorithms are proposed to derive the near-optimal solution for this problem. Finally, experimental evaluations verify that our proposed model can substantially minimize the mobile devices’ overhead by deploying computation offloading and task caching strategy reasonably.

     

Optimal dynamic spectrum allocation-assisted latency minimization for multiuser mobile edge computing

Mobile Edge Computing (MEC) has been envisioned as an efficient solution to provide computation-intensive yet latency-sensitive services for wireless devices. In this paper, we investigate the optimal dynamic spectrum allocation-assisted multiuser computation offloading in MEC for overall latency minimization. Specifically, we first focus on a static multiuser computation offloading scenario and jointly optimize users' offloading decisions, transmission durations, and Edge Servers' (ESs) resource allocations. Owing to the nonconvexity of our joint optimization problem, we identify its layered structure and decompose it into two problems: a subproblem and a top problem. For the subproblem, we propose a bisection search-based algorithm to efficiently find the optimal users' offloading decisions and ESs’ resource allocations under a given transmission duration. Second, we use a linear search-based algorithm for solving the top problem to obtain the optimal transmission duration based on the result of the subproblem. Further, after solving the static scenario, we consider a dynamic scenario of multiuser computation offloading with time-varying channels and workload. To efficiently address this dynamic scenario, we propose a deep reinforcement learning-based online algorithm to determine the near-optimal transmission duration in a real-time manner. Numerical results are provided to validate our proposed algorithms for minimizing the overall latency in both static and dynamic offloading scenarios. We also demonstrate the advantages of our proposed algorithms compared to the conventional multiuser computation offloading schemes.     

超密集网络中基于移动边缘计算的任务卸载和资源优化

移动边缘计算(MEC)通过在无线网络边缘为用户提供计算能力,来提高用户的体验质量。然而,MEC的计算卸载仍面临着许多问题。该文针对超密集组网(UDN)的MEC场景下的计算卸载,考虑系统总能耗,提出卸载决策和资源分配的联合优化问题。首先采用坐标下降法制定了卸载决定的优化方案。同时,在满足用户时延约束下采用基于改进的匈牙利算法和贪婪算法来进行子信道分配。然后,将能耗最小化问题转化为功率最小化问题,并将其转化为一个凸优化问题得到用户最优的发送功率。仿真结果表明,所提出的卸载方案可以在满足用户不同时延的要求下最小化系统能耗,有效地提升了系统性能。     

数字孪生使能的智能超表面边缘计算网络任务卸载

针对新兴的计算密集型应用对移动用户高计算性能需求问题,该文提出一种数字孪生(DT)结合智能反射面(RIS)辅助的移动边缘计算(MEC)任务卸载方案。首先,在满足用户传输功率、用户和资源设备能耗、计算资源限制条件下,通过联合优化用户卸载决策、用户传输功率、RIS相移、波束成形矢量、计算资源分配,建立一个系统能耗最小化问题;其次,将该非凸组合优化问题分解为3个子问题,使用深度双Q网络(DDQN)方法确定用户卸载策略;然后对每个训练时间步进行一次求解,基于交替迭代方法得到问题的优化解。仿真结果表明,基于DDQN的算法训练速度较快,有效降低了系统总能耗。     

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。     

User association and resource allocation in green mobile edge networks using deep reinforcement learning

In order to meet the emerging requirements for high computational complexity, low delay and energy consumption of the 5th generation wireless systems (5G) network, ultra-dense networks (UDNs) combined with multi-access edge computing ( MEC) can further improve network capacity and computing capability. In addition, the integration of green energy can effectively reduce the on-grid energy consumption of system and realize green computation. This paper studies the joint optimization of user association (UA) and resource allocation (RA) in MEC enabled UDNs under the green energy supply pattern, users need to perceive the green energy status of base stations (BSs) and choose the one with abundant resources to associate. To minimize the computation cost for all users, the optimization problem is formulated as a mixed integer nonlinear programming (MINLP) which is NP-hard. In order to solve the problem, a deep reinforcement learning ( DRL)-based association and optimized allocation (DAOA) scheme is designed to solve it in two stages. The simulation results show that the proposed scheme has good performance in terms of computationcost and time out ratio, as well achieve load balancing potentially.     

多小区蜂窝网络中计算卸载与资源分配联合优化算法

本文在多基站和远端云构成的多层计算卸载场景中,提出了一种多小区蜂窝网络中基站选择、计算卸载与资源分配联合优化算法.该算法考虑多基站重叠覆盖用户的基站选择,在边缘服务器计算资源约束条件下,构建了能耗与时延加权和的最小化问题,这是NP-hard问题.本文首先对单用户多基站计算卸载问题,采用拉格朗日乘子法对其进行求解;然后针...     

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。     

Users' experience matter: Delay sensitivity-aware computation offloading in mobile edge computing

As a promising computing paradigm, Mobile Edge Computing (MEC) provides communication and computing capability at the edge of the network to address the concerns of massive computation requirements, constrained battery capacity and limited bandwidth of the Internet of Things (IoT) systems. Most existing works on mobile edge task ignores the delay sensitivities, which may lead to the degraded utility of computation offloading and dissatisfied users. In this paper, we study the delay sensitivity-aware computation offloading by jointly considering both user's tolerance towards delay of task execution and the network status under computation and communication constraints. Specifically, we use a specific multi-user and multi-server MEC system to define the latency sensitivity of task offloading based on the analysis of delay distribution of task categories. Then, we propose a scoring mechanism to evaluate the sensitivity-dependent utility of task execution and devise a Centralized Iterative Redirection Offloading (CIRO) algorithm to collect all information in the MEC system. By starting with an initial offloading strategy, the CIRO algorithm enables IoT devices to cooperate and iteratively redirect task offloading decisions to optimize the offloading strategy until it converges. Extensive simulation results show that our method can significantly improve the utility of computation offloading in MEC systems and has lower time complexity than existing algorithms.     

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.     

基于深度强化学习的云边协同计算迁移研究

基于单一边缘节点计算、存储资源的有限性及大数据场景对高效计算服务的需求,本文提出了一种基于深度强化学习的云边协同计算迁移机制.具体地,基于计算资源、带宽和迁移决策的综合性考量,构建了一个最小化所有用户任务执行延迟与能耗权重和的优化问题.基于该优化问题提出了一个异步云边协同的深度强化学习算法,该算法充分利用了云边双方的计...     

车联网中基于NOMA-MEC的卸载策略研究

随着车联网(IoV)的迅猛发展,请求进行任务卸载的汽车终端用户也逐渐增长,而基于移动边缘计算(MEC)的通信网络能够有效地解决任务卸载在上行传输时延较高的挑战,但是该网络模型同时也面临着信道资源不足的问题。该文引入的非正交多址(NOMA)技术相较于正交多址(OMA)能够在相同的信道资源条件下为更多的用户提供任务卸载,同时考虑到任务卸载过程中多方面的影响因子,提出了混合NOMA-MEC卸载策略。该文设计了一种基于深度学习网络(DQN)的博弈算法,帮助车辆用户进行信道选择,并通过神经网络多次迭代学习,为用户提供最优的功率分配策略。仿真结果表明,该文所提出的混合NOMA-MEC卸载策略能够有效地优化多用户卸载的时延以及能耗,最大限度保证用户效益。     

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。     

Computation energy efficiency maximization based resource allocation scheme in wireless powered mobile edge computing network

For wireless powered mobile edge computing (MEC) network,a system computation energy efficiency (CEE) maximization scheme by considering the limited computation capacity at the MEC server side was proposed.Specifically,a CEE maximization optimization problem was formulated by jointly optimizing the computing frequencies and execution time of the MEC server and the edge user(EU),the transmit power and offloading time of each EU,the energy harvesting time and the transmit power of the power beacon.Since the formulated optimization problem was a non-convex fractional optimization problem and hard to solve,the formulated problem was firstly transformed into a non-convex subtraction problem by means of the generalized fractional programming theory and then transform the subtraction problem into an equivalent convex problem by introducing a series of auxiliary variables.On this basis,an iterative algorithm to obtain the optimal solutions was proposed.Simulation results verify the fast convergence of the proposed algorithm and show that the proposed resource allocation scheme can achieve a higher CEE by comparing with other schemes.     

智能超表面赋能移动边缘计算部分任务卸载策略

针对移动边缘计算(MEC)任务卸载性能易受障碍物阻挡影响的问题,该文提出一种双智能超表面(RIS)赋能的移动边缘计算任务部分卸载框架。首先,分析两个RIS之间的反射对链路增益的影响。其次,联合考虑终端用户的发射功率、终端用户的卸载速率、任务卸载量、卸载时间的分配以及RIS相移约束,旨在建立一个能耗最小化优化问题。最后,采用交替迭代算法,将原非凸问题分解为两个子问题,并利用Dinkelbach方法和最优性条件进行求解。仿真结果验证了所提算法的快速收敛特性以及在降低系统能耗方面的有效性。     

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。     

NOMA物联网下多UAV辅助MEC系统的资源分配

为解决偏远地区或突发灾害等场景中的物联网(Internet of Things, IoT)设备的任务计算问题,构建了一个非正交多址接入(Non-orthogonal Multiple Access, NOMA)-IoT(NOMA-IoT)下多无人机(Unmanned Aerial Vehicle, UAV)辅助的NOMA多址边缘计算(Multiple Access Edge Computing, MEC)系统。该系统中设备的计算能耗、卸载能耗和MEC服务器计算能耗直接受同信道干扰、计算资源和发射功率的影响,可通过联合优化卸载策略、计算资源和发射功率最小化系统加权总能耗。根据优化问题的非凸性和复杂性,提出了一种有效的迭代算法解决：首先,对固定卸载策略,计算资源和发射功率分配问题可通过连续凸逼近转化为可解的凸问题;其次,对固定计算资源和发射功率,利用联盟形成博弈解决卸载策略问题,以最小化IoT设备之间的同信道干扰。仿真结果表明,较OMA接入方式,NOMA接入方式减少本地计算能耗、卸载能耗及计算能耗约20%;较无卸载策略方法,包含卸载策略方法在减少系统加权总能耗方面效果较为明显。     

基于k-匿名的隐私保护计算卸载方法

针对移动边缘计算(MEC)中用户的卸载任务及卸载频率可能使用户被攻击者锁定的问题,该文提出一种基于k-匿名的隐私保护计算卸载方法。首先,该方法基于用户间卸载任务及其卸载频率的差异性,提出隐私约束并建立基于卸载频率的隐私保护计算卸载模型;然后,提出基于模拟退火的隐私保护计算卸载算法(PCOSA)求得最优的k-匿名分组结果和组内各任务的隐私约束频率;最后,在卸载过程中改变用户原始卸载频率满足隐私约束,最小化终端能耗。仿真结果表明,PCOSA算法能找出用户所处MEC节点下与用户卸载表现最相近的k个用户形成匿名集,有效保护了所有用户隐私。     

基于混合粒子群算法的计算卸载成本优化

为了满足用户日益增长的计算密集型和时延敏感型服务需求,同时最小化计算任务的处理成本,在时延约束下,该文针对超密集异构边缘计算网络,构建了有关任务卸载、无线资源管理、计算资源块分配的联合优化问题。考虑到所规划的问题具有非线性和混合整数的形式,且为满足约束条件及提升算法收敛速率,通过改进分层自适应搜索(HAS)算法设计了混合粒子群优化 (HPSO)算法来求解所提出的问题。仿真结果表明,HPSO算法明显优于现有算法,能有效降低任务处理成本。