网络虚拟化中动态资源分配算法研究

针对网络虚拟化中资源分配问题,提出一种动态的资源分配算法。算法根据物理节点平均负载差异度,结合当前物理网络容忍的节点负载差异动态地进行虚拟节点迁移,并通过综合影响因子为虚拟节点选择合适的目标宿主,减少虚拟节点迁移对物理链路带宽和虚拟链路时延的影响。仿真实验表明,该算法能使物理节点上的负载分布均衡,同时对时延和带宽的影响较小。     

一种侧信道风险感知的虚拟节点迁移方法

为防御网络切片(NS)中的侧信道攻击(SCA),现有的基于动态迁移的防御方法存在不同虚拟节点共享物理资源的条件过于松弛的问题。该文提出一种侧信道风险感知的虚拟节点迁移方法。根据侧信道攻击的实施特点,结合熵值法对虚拟节点的侧信道风险进行评估,并将服务器上偏离平均风险程度大的虚拟节点进行迁移;采用马尔科夫决策过程描述网络切片虚拟节点的迁移问题,并使用Sarsa学习算法求解出最终的迁移结果。仿真结果表明,该方法将恶意网络切片实例与其他网络切片实例隔离开,达到防御侧信道攻击的目的。     

一种生存性军事虚拟网络映射新方法

针对生存性的军事虚拟网络映射问题,提出了生存性的军事虚拟网络映射需要遵循的原则。构建了虚拟网络映射模型,并采用蝙蝠算法进行求解。针对故障情况,提出了区分服务的故障恢复策略,对于高优先级虚网请求提前构建保护路径,对于低优先级虚网请求则提出基于链路可靠性的故障迁移算法,为了减少带宽消耗适当考虑了节点迁移策略。最后通过仿真验证了算法在虚拟网络运行成功率、故障修复率和链路利用率方面相比其他算法具有更好的性能。     

一种碎片感知的安全虚拟网络重构方法

针对现有的虚拟网络重构算法对物理网络中产生的碎片资源考虑不够周到,导致其对在线虚拟网络映射算法的性能改善不够显著的问题,该文定义了一种网络资源碎片度度量方法,并提出一种碎片感知的安全虚拟网络重构算法。该算法通过周期性考虑物理网络中节点的碎片度,选择出待迁移虚拟节点集合;通过综合考虑物理网络的碎片度减小量和虚拟网络的映射开销减少量,选择出最佳的虚拟节点迁移方案。仿真结果表明,该算法的请求接受率和收益开销比均优于当前的重构算法,特别是在收益开销比方面的优势更加明显。     

基于集成深度神经网络流量预测的动态网络切片迁移算法

针对5G网络切片(NS)场景下由于缺乏提前对物理网络资源进行感知而导致切片迁移滞后的问题,该文提出一种基于集成深度神经网络流量预测的动态切片调整和迁移算法(DSAM)。首先建立了基于计算、内存、带宽资源配置的网络总惩罚模型;其次,提出基于集成深度神经网络的流量预测算法预测未来网络流量情况,并根据流量类型的不同将其转换成对未来时刻物理网络的资源占用及切片的资源需求感知;最后,根据感知结果,以尽可能大地降低运营商惩罚为目标,通过动态切片调整和迁移策略将虚拟网络功能(VNF)和虚拟链路迁移到满足资源限制的物理节点和链路上。仿真结果表明,所提算法有效提高了切片迁移的效率和网络资源利用率。     

基于深度信念网络资源需求预测的虚拟网络功能动态迁移算法

针对5G网络场景下缺乏对资源需求的有效预测而导致的虚拟网络功能(VNF)实时性迁移问题,该文提出一种基于深度信念网络资源需求预测的VNF动态迁移算法。该算法首先建立综合带宽开销和迁移代价的系统总开销模型,然后设计基于在线学习的深度信念网络预测算法预测未来时刻的资源需求情况,在此基础上采用自适应学习率并引入多任务学习模式优化预测模型,最后根据预测结果以及对网络拓扑和资源的感知,以尽可能地减少系统开销为目标,通过基于择优选择的贪婪算法将VNF迁移到满足资源阈值约束的底层节点上,并提出基于禁忌搜索的迁移机制进一步优化迁移策略。仿真表明,该预测模型能够获得很好的预测效果,自适应学习率加快了训练网络的收敛速度,与迁移算法结合在一起的方式有效地降低了迁移过程中的系统开销和服务级别协议(SLA)违例次数,提高了网络服务的性能。     

无线传感网络布局的虚拟力导向微粒群优化策略

无线传感网络通常由固定传感节点和少量移动传感节点构成,动态无线传感网络布局优化有利于提高无线传感网络覆盖率和目标检测概率,是无线传感网络研究的关键问题之一.传统的虚拟力算法在优化过程中容易受固定传感节点的影响,无法实现全局优化.本文结合虚拟力算法和微粒群算法,提出一种面向无线传感网络布局的虚拟力导向微粒群优化策略.该策略通过无线传感节点间的虚拟力影响微粒群算法的速度更新过程,指导微粒进化,加快算法收敛.实验表明,虚拟力导向微粒群优化策略能快速有效地实现无线传感节点布局优化.与微粒群算法和虚拟力算法相比,虚拟力导向微粒群优化策略不仅网络覆盖率高,且收敛速度快,耗时少.     

一种基于Viterbi算法的虚拟网络功能自适应部署方法

为了应对移动数据流量的爆炸性增长,5G移动通信网将引入新型的架构设计。软件定义网络和网络功能虚拟化是网络转型的关键技术,将驱动移动通信网络架构的创新,服务链虚拟网络功能的部署是网络虚拟化研究中亟待解决的问题。该文针对已有部署方法未考虑服务链中虚拟网络功能间顺序约束和移动业务特点的问题,提出一种基于Viterbi算法的虚拟网络功能自适应部署方法。该方法实时感知底层节点的资源变化并动态调整拓扑结构,采用隐马尔科夫模型描述满足资源约束的可用的底层网络节点拓扑信息,基于Viterbi算法在候选节点中选择时延最短的服务路径。实验表明,与其它的虚拟网络功能部署方法相比,该方法降低了服务链的服务处理时间,并提高了服务链的请求接受率和底层资源的成本效率。     

面向目标跟踪的物联网感知层节点部署优化研究

针对目标跟踪物联网感知层节点动态部署的特点,在人工鱼群算法和虚拟力算法的基础上,设计了融入虚拟力影响的人工鱼群控制算法,给出了算法的参数自适应调整策略,该算法利用节点间的虚拟力来影响人工鱼的觅食行为和追尾行为,指导人工鱼群的进化过程,加快算法的收敛性。仿真实验结果显示,算法能快速有效地实现无线传感器网络节点的部署优化,与人工鱼群算法和虚拟力算法相比,该算法不仅全局寻优能力强,且收敛速度快,可有效提高网络覆盖率,优化网络性能。     

一种改进的一致性哈希算法

一致性哈希算法常用于分布式系统的负载均衡,常见的算法存在一些弊端,如传统的带虚拟节点的一致性哈希算法在工程应用中节点负载不完全均衡,谷歌跳跃一致性哈希和腾讯PaxosStore存储系统的一致性哈希算法只能从后往前删除节点,同时难以应用于异构系统。针对上述问题,文章提出了一种改进的一致性哈希算法,优化了虚拟节点的分配,在同构系统中通过初始化时均匀分配虚拟节点、添加删除节点时从盈余向不足迁移虚拟节点的方法,保证了算法的一致性,并且当虚拟节点数远大于实节点数时系统可实现接近完全的均衡,增删节点也不受位置的限制。在异构系统中,算法通过按节点性能比例分配和迁移虚拟节点的方法,实现了对负载和流量的精准分配。对初始的虚拟节点数(N值)也进行了讨论,可以根据系统均衡性要求配置N值,并给出了重新均衡系统时分裂虚拟节点和扩大N值的算法。     

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.     

Mobility aware edge service migration strategy

To address the problem of load imbalance among edge servers and quality of service degradation caused by dynamic changes of user locations in mobile edge computing networks,a mobility aware edge service migration algorithm was proposed.Firstly,the optimization problem was formulated as a mix integer nonlinear programming problem,with the goal of minimizing the perceived delay of user service request.Then,the delay optimization problem was decoupled into the edge service migration and edge node selection sub-problems based on the Lyapunov optimization approach.Thereafter,the fast edge decision algorithm was proposed to optimize the resource allocation and edge service migration under a given radio access strategy.Finally,the asynchronous optimal response algorithm was proposed to iterate out the optimal radio access strategy.Simulation results validate the proposed algorithm can reduce the perceived delay under the service migration cost constraint while comparing with other existing algorithms.     

Dynamic service migration strategy based on MDP model with multiple parameter in vehicular edge network

To handle with the service interruption caused by vehicles’ mobility and limited service coverage of edge servers,a dynamic service migration algorithm based on multi-parameters Markov decision process (MDP) model was put forward for vehicular edge network,which was called as dynamic service migration algorithm based on multiple parameter (DSMMP).Combining delay,bandwidth,server capacity with vehicle motion information,DSMMP constructed a multi-parameters MDP revenue function to remedy the deficiency of distance-based schemes.By using vehicle motion and delay constraints,a candidate server set with several candidate servers was defined,and migration decision through long-term Bellman revenue values was made.In order to improve the dynamic adaptability of the proposed algorithm,the weight values were calculated and updated by leveraging historical information.Simulation results show that our strategy has a good performance in terms of delay,packet loss ratio and service migration times.     

Towards efficiently migrating virtual networks in cloud-based data centers

With the expansion of cloud computing, virtual network (VN) migration becomes the very perspective technology for saving energy, ensuring Service Level Agreements or improving the survivability of virtual networks in cloud networks. At present, the majority of research on the VN migration, however, are for saving energy or improving resource utilizations, and few of them for the entire virtual network migration for guaranteeing QoS or improving the survivability of virtual networks. Since the regional failure, network maintenance or QoS violation, the service provider generally needs to migrate the VN for guaranteeing the QoS or improving the survivability of virtual networks. In the paper, we research the live migration problem of the virtual network to optimize the virtual network migration performance. To efficient migrate virtual network, we present an effective VN migration method, VNM. To control the cost of migration or migration traffic, based on the VNM algorithm, we present an effective VN migration method with migration traffic control, VNM-MTC. We use two networks as substrate networks to simulate the performances of our presented algorithms. From the experiment, we can see that the total VN reconfiguration cost, total VN redeployment cost, total VN migration cost and blocking ratio of our presented algorithms are better than that of the contrast algorithm.     

Migration cost optimization for service provider legacy network migration to software-defined IPv6 network

This paper studies a problem for seamless migration of legacy networks of Internet service providers to a software-defined networking (SDN)-based architecture along with the transition to the full adoption of the Internet protocol version 6 (IPv6) connectivity. Migration of currently running legacy IPv4 networks into such new approaches requires either upgrades or replacement of existing networking devices and technologies that are actively operating. The joint migration to SDN and IPv6 network is considered to be vital in terms of migration cost optimization, skilled human resource management, and other critical factors. In this work, we first present the approaches of SDN and IPv6 migration in service providers' networks. Then, we present the common concerns of IPv6 and SDN migration with joint transition strategies so that the cost associated with joint migration is minimized to lower than that of the individual migration. For the incremental adoption of software-defined IPv6 (SoDIP6) network with optimum migration cost, a greedy algorithm is proposed based on optimal path and the customer priority. Simulation and empirical analysis show that a unified transition planning to SoDIP6 network results in lower migration cost.     

边缘计算多约束可信协同任务迁移策略

为保障边缘计算的服务质量,提出一种在多约束条件下边缘计算可信协同任务迁移策略。该策略基于任务需求,由边缘计算协同服务盟主节点组织调度协同服务盟员,基于用户任务迁移的K维权重指标,确定协同盟员调度优先级,以盟员负载均衡性为适应函数,通过贪心算法执行盟员任务分配与调度,基于路由捎带选择备用节点,通过迁移优先级评估,实现协同服务异常时的调度和迁移,由此提高边缘计算任务迁移的服务质量,保障任务迁移的可靠性。仿真实验表明,该机制能有效完成协同任务分发与迁移调度,提高边缘计算协同效率,保障网络服务质量。     

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。     

云环境下基于迁移的虚拟机集群优化算法

针对云环境中虚拟机集群负载不均衡问题,提出一种基于虚拟机迁移的集群优化算法。通过对节点负载的实时监测,动态调整各种资源的权重,根据资源权重选择可最大程度降低主机负载的虚拟机进行迁移。该算法利用预测机制,消除主机资源利用率的临时越界引起的不必要的虚拟机迁移。在选择目标节点时,采用多目标决策法,兼顾多资源匹配率,服务级目标违背率(SLA)等多种管理目标。实验结果表明,与同类型的负载均衡算法相比,该算法能减少迁移次数,降低SLA违背率。     

A new approach for service migration in cloud‐based e‐commerce using an optimization algorithm

Service‐oriented architecture (SOA) has a crucial role in backing productive cloud services. Also, the vast spread of the theoretical notion of diverse businesses (like e‐commerce) into the actual use has been recently applied by cloud computing. The service functionality could be affected by overfilling of the network traffic because of the broadly dispersed nature of e‐commerce in clouds—a key challenge for immediate jobs. Throughout the last decade, a vast range of applications or large‐scale operators has increasingly attracted to migrate the services in clouds. An effective method for accessing the applications throughout standard business hours is continually moving virtual machine containers from one data center to another. Now, with the commonness of cloud computing, many applications have been moved to the cloud fully/partly. It can be handled through the migration of cloud services to diverse platforms in a way that minimizes the communication cost of e‐commerce. As this issue has an NP‐hard nature, in the present article, we present an automatic smart service migration outline through the ant colony optimization (ACO) algorithm on cloud‐oriented e‐commerce. In the presented model, we use the ACO algorithm to take the finest (near‐optimal) service migration decisions. Based on the obtained results, the proposed technique has the optimal number of migrations compared to the existing models.     

Proactive migration model of SWIM service based on situation awareness

To solve the problem that in the system wide information management (SWIM) network,the SWIM service provider suffers from SWIM service interruption,service delay increase or service quality degradation due to malicious attack or self-failure.Therefore,a proactive migration model of SWIM service was proposed on the basis of situation awareness,which used the random forest algorithm to timely judge the SWIM service provider security situation.SWIM service authority was actively migrated according to security situation,and the emergencies impact on SWIM services were reduces.Experimental results show that the proposed model can guarantee services continuity in an emergency event,which has higher reliability and stability than SWIM network in which the service migration model is not deployed.