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。     

一种面向随机计算卸载的两层无人机能耗优化方法

当物联网设备(Internet of Things Device,IoTD)面临随机到达且复杂度高的计算任务时,因自身计算资源和能力所限,无法进行实时高效的处理。为了应对此类问题,设计了一种两层无人机辅助的移动边缘计算(Mobile Edge Computing,MEC)模型。在该模型中,考虑到IoTD处理随机计算任务时的局限性,引入多架配备MEC服务器的下层无人机和单架上层无人机进行协同处理。为了实现系统能耗最优化,提出了一种资源优化和多无人机位置部署方案,根据计算任务到达的随机性,应用李雅普诺夫优化方法将能耗最小化问题转化为一个确定性问题,应用差分进化(Differential Evolution,DE)算法进行多次变异、交叉和选择取得无人机的优化部署方案;采用深度确定性策略梯度(Depth Deterministic policy Gradient,DDPG)算法对带宽分配、计算资源分配、传输功率分配和任务卸载分配进行联合优化。实验结果表明,该算法相较于对比算法系统能耗降低35%,充分验证了其可行性和有效性。     

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。     

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.

     

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.     

DDPG-based intelligent rechargeable fog computation offloading for IoT

In view of the existing computation offloading research on fog computing network scenarios, most scenarios focus on reducing energy consumption and delay and lack the joint consideration of smart device rechargeability. This paper proposes a deep deterministic policy gradient-based intelligent rechargeable fog computation offloading mechanism that is combined with simultaneous wireless information and power transfer technology. Specifically, an optimization problem that minimizes the total energy consumption for completing all tasks in a multiuser scenario is formulated, and the joint optimization of the task offloading ratio, uplink channel bandwidth, power split ratio and computing resource allocation is fully considered. Based on the above nonconvex optimization problem with a continuous action space, a communication, computation and energy harvesting co-aware intelligent computation offloading algorithm is developed. It can achieve the optimal energy consumption and delay, and similar to a double deep Q-network, an inverting gradient updating-based dual actor-critic neural network design can improve the convergence and stability of the training process. Finally, the simulation results validate that the proposed mechanism can converge quickly and can effectively reduce the energy consumption with the lowest task delay.

     

基于无人机无线能量传输的边缘计算系统能耗优化方法研究

无线能量传输(WPT)和移动边缘计算(MEC)可以为无线设备提供能量供应和任务计算,有效提高设备的能量效率.该文提出一种基于无人机无线能量传输的边缘计算系统能耗优化方法,在所提方法中,通过联合优化能量收集(EH)时间、用户发射功率和卸载决策,最小化系统总能耗.利用块坐标下降法(BCD),将优化问题分解为两个子问题,通过...     

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。     

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...     

基于深度强化学习的无人机辅助移动边缘计算系统能耗优化

近年来,部署搭载有移动边缘计算(MEC)服务器的无人机(UAVs)为地面用户提供计算资源已成为一种新兴的技术。针对无人机辅助多用户移动边缘计算系统,该文构建了以最小化用户平均能耗为目标的模型,联合优化无人机的飞行轨迹和用户计算策略的调度。通过深度强化学习(DRL)求解能耗优化问题,提出基于柔性参与者-评论者(SAC)的优化算法。该算法应用最大熵的思想来探索最优策略并使用高效迭代更新获得最优策略,通过保留所有高回报值的策略,增强算法的探索能力,提高训练过程的收敛速度。仿真结果表明与已有算法相比,所提算法能有效降低用户的平均能耗,并具有很好的稳定性和收敛性。     

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.     

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。     

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。     

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。     

面向空天地异构网络的边缘计算部分任务卸载策略

空天地异构网络作为一种新型网络构架,是未来6G实现泛在连接的关键支撑。该文提出一种面向空天地异构网络(SAGIN)的移动边缘计算部分任务卸载方案。首先,分析了低轨(LEO)卫星的覆盖时间。其次,联合考虑用户与无人机(UAV)匹配关联因子、任务分配、带宽分配、无人机计算资源分配以及无人机轨迹,旨在建立一个能耗最小化问题。最后,采用交替迭代优化算法,将原非凸问题分解为3个子问题,并利用变量替换和连续凸逼近方法将问题转化为凸问题进行求解。仿真结果表明,所提算法具有良好的收敛性能,并有效地降低系统能耗。     

Joint resource allocation for hybrid NOMA-assisted MEC in 6G networks

Multi-access Edge Computing (MEC) is an essential technology for expanding computing power of mobile devices, which can combine the Non-Orthogonal Multiple Access (NOMA) in the power domain to multiplex signals to improve spectral efficiency. We study the integration of the MEC with the NOMA to improve the computation service for the Beyond Fifth-Generation (B5G) and the Sixth-Generation (6G) wireless networks. This paper aims to minimize the energy consumption of a hybrid NOMA-assisted MEC system. In a hybrid NOMA system, a user can offload its task during a time slot shared with another user by the NOMA, and then upload the remaining data during an exclusive time duration served by Orthogonal Multiple Access (OMA). The original energy minimization problem is non-convex. To efficiently solve it, we first assume that the user grouping is given, and focuses on the one group case. Then, a multilevel programming method is proposed to solve the non-convex problem by decomposing it into three subproblems, i.e., power allocation, time slot scheduling, and offloading task assignment, which are solved optimally by carefully studying their convexity and monotonicity. The derived solution is optimal to the original problem by substituting the closed expressions obtained from those decomposed subproblems. Furthermore, we investigate the multi-user case, in which a close-to-optimal algorithm with low-complexity is proposed to form users into different groups with unique time slots. The simulation results verify the superior performance of the proposed scheme compared with some benchmarks, such as OMA and pure NOMA.     

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.     

Learning for Smart Edge: Cognitive Learning-Based Computation Offloading

With the development of intelligent applications, more and more intelligent applications are computation intensive, data intensive and delay sensitive. Compared with traditional cloud computing, edge computing can reduce communication delay by offloading computing tasks to edge cloud. Furthermore, with the complexity of computing scenarios in edge cloud, deep learning based on computation offloading scheme has attracted wide attention. However, all the learning-based offloading scheme does not consider the where and how to run the offloading scheme itself. Thus, in this paper, we consider the problem of running the learning-based computation offloading scheme for the first time and propose the learning for smart edge architecture. Then, we give the computation offloading optimization problem of mobile devices under multi-user and multi edge cloud scenarios. Furthermore, we propose cognitive learning-based computation offloading (CLCO) scheme for this problem. Finally, experimental results show that compared with other offloading schemes, the CLCO scheme has lower task duration and energy consumption.

     

Energy-efficient task offloading strategy in mobile edge computing for resource-intensive mobile applications

Mobile Edge Computing (MEC) has been considered a promising solution that can address capacity and performance challenges in legacy systems such as Mobile Cloud Computing (MCC). In particular, such challenges include intolerable delay, congestion in the core network, insufficient Quality of Experience (QoE), high cost of resource utility, such as energy and bandwidth. The aforementioned challenges originate from limited resources in mobile devices, the multi-hop connection between end-users and the cloud, high pressure from computation-intensive and delay-critical applications. Considering the limited resource setting at the MEC, improving the efficiency of task offloading in terms of both energy and delay in MEC applications is an important and urgent problem to be solved. In this paper, the key objective is to propose a task offloading scheme that minimizes the overall energy consumption along with satisfying capacity and delay requirements. Thus, we propose a MEC-assisted energy-efficient task offloading scheme that leverages the cooperative MEC framework. To achieve energy efficiency, we propose a novel hybrid approach established based on Particle Swarm Optimization (PSO) and Grey Wolf Optimizer (GWO) to solve the optimization problem. The proposed approach considers efficient resource allocation such as sub-carriers, power, and bandwidth for offloading to guarantee minimum energy consumption. The simulation results demonstrate that the proposed strategy is computational-efficient compared to benchmark methods. Moreover, it improves energy utilization, energy gain, response delay, and offloading utility.     

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.