移动性感知的边缘服务迁移策略

针对移动边缘计算网络中由于用户位置动态变化而导致边缘服务器间负载不均衡、用户服务质量降低的问题,提出了一种移动性感知的边缘服务迁移算法。首先,以最小化用户服务请求感知时延为目标,将优化问题建模为混合整数非线性规划问题。其次,基于Lyapunov优化方法将时延优化问题解耦为边缘服务迁移子问题与无线接入子问题。再次,提出快速边缘决策算法求解出给定无线接入策略情况下最优的资源分配与边缘服务迁移方案。最后,提出异步最佳响应算法迭代出最优无线接入策略。仿真结果表明,与现有服务迁移策略相比较,所提算法能够在保证服务迁移成本稳定的情况下降低用户服务请求的感知时延。     

一种车载服务的快速深度Q学习网络边云迁移策略

智能网联交通系统中车载用户的高速移动，不可避免地造成了数据在边缘服务器之间频繁迁移，产生了额外的通信回传时延，对边缘服务器的实时计算服务带来了巨大的挑战。为此，该文提出一种基于车辆运动轨迹的快速深度Q学习网络(DQN-TP)边云迁移策略，实现数据迁移的离线评估和在线决策。车载决策神经网络实时获取接入的边缘服务器网络状态和通信回传时延，根据车辆的运动轨迹进行虚拟机或任务迁移的决策，同时将实时的决策信息和获取的边缘服务器网络状态信息发送到云端的经验回放池中；评估神经网络在云端读取经验回放池中的相关信息进行网络参数的优化训练，定时更新车载决策神经网络的权值，实现在线决策的优化。最后仿真验证了所提算法与虚拟机迁移算法和任务迁移算法相比能有效地降低时延。     

Enhancing live virtual machine migration process via optimized resource allocation in next generation mobile edge network: A hybrid evolutionary approach

The evolution of 5th Generation wireless technology introduced Mobile Edge Computing, where edge servers are placed at the edge of the network, and are associated with evolved Node Base Stations (eNBs). This enables mobile users to offload their resource‐intensive tasks to these servers and improve network performance by reducing end‐to‐end delay. However, frequent user mobility leads to frequent re‐planning of network and increases network load. This demands dynamic Virtual Machine (VM) migration in Mobile Edge paradigm for an improved Quality of Service (QoS). For an enhanced VM migration process, an optimal pair of migrating VMs and destination edge servers needs to be chosen. In this paper, we propose an optimized decision‐making policy that chooses such optimal pairs. Several decision parameters such as average wait time, processing delay, migration delay, transmission power, and processing power are modeled. A profit function is developed using these modeled decision parameters that chooses the optimal pairs. This function is maximized using the proposed hybrid evolutionary algorithm, which combines the advantages of PSO and GA. The pairs are chosen in such a manner, that the selection guarantees high network throughput, reduced service delay, and energy consumption which is reflected in the simulation.     

Service migration in mobile edge computing: A deep reinforcement learning approach

In mobile edge computing, service migration can not only reduce the access latency but also reduce the network costs for users. However, due to bandwidth bottleneck, migration costs should also be considered during service migration. In this way, the trade-off between benefits of service migration and total service costs is very important for the cloud service providers. In this paper, we propose an efficient dynamic service migration algorithm named SMDQN, which is based on reinforcement learning. We consider each mobile application service can be hosted on one or more edge nodes and each edge node has limited resources. SMDQN takes total delay and migration costs into consideration. And to reduce the size of Markov decision process space, we devise the deep reinforcement learning algorithm to make a fast decision. We implement the algorithm and test the performance and stability of it. The simulation result shows that it can minimize the service costs and adapt well to different mobile access patterns.     

V2X多节点协同分布式卸载策略

为了应对车联网中计算资源密集、可分离型任务的卸载环境动态变化和不同协同节点通信、计算资源存在差异的问题,提出了一种在V2X下多协同节点串行卸载、并行计算的分布式卸载策略。该策略利用车辆可预测的行驶轨迹,对任务进行不等拆分,分布式计算于本地、MEC及协同车辆,建立系统时延最小化的优化问题。为求解该优化问题,设计了博弈论的卸载机制,以实现协同节点串行卸载的执行顺序;鉴于车联网的动态时变特性,利用序列二次规划算法,给出了最优的任务不等拆分。仿真结果表明,所提策略能够有效减少计算任务系统时延,且当多协同节点分布式卸载服务时,所提策略在不同的参数条件下仍然能够保持稳定的系统性能。     

V2X多节点协同分布式卸载策略

为了应对车联网中计算资源密集、可分离型任务的卸载环境动态变化和不同协同节点通信、计算资源存在差异的问题,提出了一种在V2X下多协同节点串行卸载、并行计算的分布式卸载策略。该策略利用车辆可预测的行驶轨迹,对任务进行不等拆分,分布式计算于本地、MEC及协同车辆,建立系统时延最小化的优化问题。为求解该优化问题,设计了博弈论的卸载机制,以实现协同节点串行卸载的执行顺序;鉴于车联网的动态时变特性,利用序列二次规划算法,给出了最优的任务不等拆分。仿真结果表明,所提策略能够有效减少计算任务系统时延,且当多协同节点分布式卸载服务时,所提策略在不同的参数条件下仍然能够保持稳定的系统性能。     

运营商网络中基于深度强化学习的服务功能链迁移机制

为改善运营商网络提供的移动服务体验,该文研究服务功能链(SFC)的在线迁移问题。首先基于马尔可夫决策过程(MDP)对服务功能链中的多个虚拟网络功能(VNF)在运营商网络中的驻留位置迁移进行模型化分析。通过将强化学习和深度神经网络相结合提出一种基于双深度Q网络(double DQN)的服务功能链迁移机制,该迁移方法能在连续时间下进行服务功能链的在线迁移决策并避免求解过程中的过度估计。实验结果表明,该文所提出的策略相比于固定部署算法和贪心算法在端到端时延和网络系统收益等方面优势明显,有助于运营商改善服务体验和资源的使用效率。     

基于协作信誉和设备反馈的物联网边缘服务器信任评估算法

针对边缘服务器的安全问题,提出了一种集成了服务器协作信誉以及设备用户反馈的信任评估算法来提高边缘计算上下文的安全性.交互过程中,使用了一种基于客观信息熵理论的融合算法来聚合服务器间的协作信誉,同时采用了部分同态加密算法来防止交互过程中用户数据的泄露.交互结束后,选择高可信的设备节点计算反馈信任,克服了传统机制的恶意反馈...     

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。     

移动边缘网络中基于用户移动的服务功能链迁移策略

移动边缘计算(Mobile Edge Computing,MEC)通过在网络边缘部署服务器,提供计算和存储资源,可为用户提供超低时延和高带宽业务。网络功能虚拟化(Network Function Virtualization,NFV)与MEC技术相结合,可在MEC服务器上提供服务功能链(Service Function Chain,SFC),提升用户的业务体验。为了保证移动用户的服务质量,需要在用户跨基站移动时将SFC迁移到合适的边缘服务器上。主要以最小化用户服务的端到端时延和运行成本为目标,提出了MEC网络中具有资源容量约束的SFC迁移策略,以实现移动用户业务的无缝迁移。仿真结果表明,与现有方案相比,该策略具有更好的有效性和高效性。     

Estimation‐Based Load‐Balancing with Admission Control for Cluster Web Servers

The growth of the World Wide Web and web‐based applications is creating demand for high performance web servers to offer better throughput and shorter user‐perceived latency. This demand leads to widely used cluster‐based web servers in the Internet infrastructure. Load balancing algorithms play an important role in boosting the performance of cluster web servers. Previous load balancing algorithms suffer a significant performance drop under dynamic and database‐driven workloads. We propose an estimation‐based load balancing algorithm with admission control for cluster‐based web servers. Because it is difficult to accurately determine the load of web servers, we propose an approximate policy. The algorithm classifies requests based on their service times and tracks the number of outstanding requests from each class in each web server node to dynamically estimate each web server load state. The available capacity of each web server is then computed and used for the load balancing and admission control decisions. The implementation results confirm that the proposed scheme improves both the mean response time and the throughput of clusters compared to rival load balancing algorithms and prevents clusters being overloaded even when request rates are beyond the cluster capacity.     

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.     

An eigenvalue‐based edge infrastructure for cloud‐based CDN

In today's dynamic video landscape, an end user needs services to be delivered to any devices anytime with less delay over the Internet. Now users' expectation has changed; they want faster time‐to‐market, cost reduction, and the ability to adjust according to the evolving requirements, which are a limit for the traditional server‐based approach. The explosive growth of the internet multimedia application needs a new approach to content delivery to overcome the limitations of server‐based techniques. Cloud‐based content delivery networks (CCDNs) have recently started to emerge where contents are cached from the cloud storage and delivered through the distribution service to meet quality of services (QoS) of requested services. In this paper, we dealt with CCDN deployment problem and proposed a new eigenvalue‐based edge infrastructure for a network service provider to serve the users with a variation on proximity interest concerning operational cost and user QoS satisfaction. The edge infrastructure designing is a two‐step process: (a) ideal location search for placing edge server and (b) edge server placement and capacity provisioning. The performance of the proposed approach is appraised via modeling and simulation. Performance evaluation outcomes are exhibited to manifest the effectiveness and competitiveness of our approach when compared with existing algorithms.     

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...     

Service function chain embedding algorithm with wireless multicast in mobile edge computing network

To resolve the excessive system overhead and serious traffic congestion in user-oriented service function chain (SFC) embedding in mobile edge computing (MEC) networks,a content-oriented joint wireless multicast and SFC embedding algorithm was proposed for the multi-base station and multi-user edge networks with MEC servers.By involving four kinds of system overhead,including service flow,server function sustaining power,server function service power and wireless transmission power,an optimization model was proposed to jointly design SFC embedding with multicast beamforming.Firstly,with Lagrangian dual decomposition,the problem was decoupled into two independent subproblems,namely,SFC embedding and multicast beamforming.Secondly,with the L_p norm penalty term-based successive convex approximation algorithm,the integer programming-based SFC embedding problem was relaxed to an equivalent linear programming one.Finally,the non-convex beamforming optimization problem was transformed into a series of convex ones via the path following technique.Simulation results revealed that the proposed algorithm has good convergence,and is superior to both the optimal SFC embedding with unicasting and random SFC embedding with multicasting in terms of system overhead.     

基于epsilon-greedy的边缘服务器选择模型

如今,5G的时代已经到来,万物互联成为可能。在这种情况下,移动通信技术在人们日常生活和社会发展中的地位进一步突出。用户本地的计算卸载到边缘服务器中,从而解决用户设备在计算性能、存储等方面的不足。一般来说,一个用户周围会存在多个边缘服务器,由此便引发了边缘服务器的选择问题。文章重点介绍了在5G的背景下基于epsilon-greedy的边缘服务器选择问题,以及多臂老虎机模型、epsilon-greedy算法,多臂老虎机模型实现边缘服务器选择,对比了随机选择和epsilon-greedy的优劣。     

Method of privacy protection based on multiple edge servers in personalized search

In the plaintext environment,users' personalized search results can be obtained through users' interest model and query keywords.However,it may possibly result in the disclosure of sensitive data and privacy,which prevents using sensitive data in cloud search.Therefore,data is generally stored in the form of ciphertext in the cloud server.In the process of cloud search service,users intend to quickly obtain the desired search results from the vast amount of ciphertext.In order to solve the problem,it was proposed that a method of privacy protection based on multiple edge servers in personalized search shall be used.By introducing multiple edge servers and cutting the index as well as the query matrix,the computing relevance scores of partial query and partial file index are achieved on the edge server.The cloud server only needs to get the relevance score on the edge server and make a simple processing that can return to the most relevant Top K files by user query,so as to make it particularly suitable for a large number of users in the massive personalized ciphertext search.Security analysis and experimental results show that this method can effectively protect users’ privacy and data confidentiality.In addition,it can guarantee high efficiency in search to provide better personalized search experience.     

基于任务生灭过程模型的边缘计算批处理调度算法分析与设计

移动边缘计算技术为低时延要求、资源敏感的计算任务需求提供解决方案,通过研究任务请求特征以提高调度算法效率是边缘计算的重要研究方向。不同于现有研究将任务请求特征建模为单一随机变量的做法,提出基于任务请求生灭过程模型的边缘计算架构,将求解最优调度决策的过程建模为无限期平均成本马尔可夫决策过程。在使用贝尔曼方程分析问题的过程中,利用任务的生灭特性对未来的请求到达做出估计以判断当前决策对未来系统时延能耗成本的影响,进而辅助确定当前状态的最优决策,并结合任务相关性感知提出批处理任务调度控制算法。所提算法根据生灭状态信息对策略迭代的状态空间和决策空间进行剪枝以降低策略改进的复杂度,突破了策略迭代算法的复杂度瓶颈。仿真结果表明,所提算法相较于传统的策略迭代算法具有明显的低复杂度优势,且能在不同系统条件下保持低时延、能耗成本。     

基于自然梯度Actor-Critic强化学习的卫星边缘网络服务功能链部署方法

鉴于低轨卫星网络的高动态性和空间环境的复杂性,如何提供在线的快速服务功能链(SFC)部署方法,成为低轨卫星边缘网络中亟待解决的问题。综合考虑节点和链路容量等约束以及服务迁移等切换代价,针对部署多接入边缘计算(MEC)服务器的低轨卫星网络,该文提出一种基于自然梯度参与者-评价者(Actor-Critic)强化学习架构的SFC在线部署方法。首先,针对低轨卫星网络的环境高动态性,对实时容量约束和迁移代价进行建模;其次,引入马尔可夫决策过程(MDP),综合考虑服务迁移和卫星坐标等因素,描述低轨卫星网络的状态转移过程;最后,提出一种基于自然梯度的在线SFC部署强化学习方法,不同于标准梯度,自然梯度法进行模型层面的更新,以避免神经网络的训练陷入局部最优解。仿真结果表明,该文方法可逼近全局最优解,并在端到端时延性能上优于基于标准梯度的强化学习部署方法。     

基于北斗和边缘计算的车联网导航技术研究

随着车辆保有量的不断增长和车联网应用的普及,车辆终端会产生大量需要实时处理的数据消息。在车辆高速移动场景下,传统的车联网导航系统由于车辆差分定位数据存在传输时延,导致车辆定位结果存在一定的偏差,无法及时获得高精度定位结果。基于此,文中提出了一种基于北斗定位和边缘计算的车联网导航技术方案,采用改进的遗传算法进行终端定位请求的资源分配,有效降低整个边缘网络的服务时延,并利用基于边缘节点的优化无损卡尔曼滤波算法来提高车联网节点的定位精度。实验表明,文中所提出的方法能够为大规模车联网终端提供实时精准、低延迟和高精度的定位服务,具有较高的实际应用价值。