基于拓扑结构感知的节点多属性网络映射算法

针对当前节点多属性网络链路映射长度较长、网络请求接受率和收益开销较低的问题,提出基于拓扑结构感知的节点多属性网络映射算法.根据无向图描述节点多属性网络映射问题,采用拓扑结构感知,构建节点多属性网络模型和节点链路映射评测指标,利用回溯算法,计算sumTR值,获得备选网络节点集合.使用子区域作为物理节点映射区域进行资源分配,按照映射优先级排列网络节点依次映射,分析节点多属性,使用最短路径算法,排序跳数最小链路映射,实现节点多属性网络映射.实验结果表明,所提算法能够有效缩短链路映射长度,提高网络请求接受率和收益开销.     

节点与链路协同映射的生存性虚拟光网络映射算法

针对弹性光网络中单链路故障问题,提出一种基于匈牙利算法求解链路映射方案的节点与链路协同映射保护算法CMST-HA。将虚拟网络请求的节点与链路分别划分为主动类型与被动类型,把主动类型节点映射至邻接链路频谱资源丰富且邻接节点计算资源充足的物理节点上,在主动链路时使用匈牙利算法求解出最小映射开销方案并完成映射,确定被动节点的映射位置,利用KSP算法为被动链路选择映射路径,在此基础上为虚拟网络请求的最小生成树链路提供备份路径。仿真结果表明,与RVNM、CMST算法相比,CMST-HA算法不仅能够降低虚拟网络请求阻塞率,而且可增加物理网络收益。     

基于实时拓扑属性的虚拟网络映射算法（英文）

研究目的:基于虚拟网络请求和底层物理网络实时拓扑属性,提出一种高效的两步式虚拟网络映射算法。创新要点:分别利用中介中心性和物理节点相关性对虚拟网络请求和底层物理网络中节点进行重要性评估,在此基础上给出一种两步式映射算法(算法1,2)。研究方法:首先给出中间中心性、接近中心性以及节点相关性计算模型,结合节点本地资源分别提出虚拟网络请求和物理网络中节点排名计算方式。当虚拟网络请求到达后,根据虚拟节点排名,将其映射到拥有足够资源的物理节点中排名最靠前的节点。节点映射完成后,使用K-th最短路径算法进行链路映射。映射过程中采用文献(Yu et al.,2008)中所使用的时间窗口模式进行接入控制。重要结论:利用节点本地资源,针对性分析虚拟网络请求和物理网络实时拓扑属性,提出两步式映射算法。该算法提高请求接受率、开销收益比的同时减少算法映射时间,取得更好的映射效果(图3-10)。     

基于强化学习的高可靠性多域虚拟网络映射算法

现有的虚拟网络映射算法大多是依赖于人工规则对节点进行排序,决定节点先后映射的顺序,来优化节点映射从而提高虚拟网络请求的成功率。而在链路映射阶段普遍采用广度优先搜索算法,忽略了节点资源和链路资源具有强相关性的特点,从而只能取得局部最优的映射结果。针对上述问题,基于5G多域异构网络环境,从网络的可生存性的保护角度出发,提出一种使用双层强化学习的虚拟网络映射算法。将强化学习同时应用于网络映射的节点和链路两阶段,使用梯度策略和反向传播的方法对该网络模型进行训练,并使用此训练模型完成映射。仿真结果表明,与对比算法相比,该算法在优化节点映射的同时优化了链路映射,且在映射成功率、长期收益率、节点和链路的利用率等方面均取得较好结果。     

基于熵权VIKOR的安全虚拟网络映射算法

近年来,虚拟网络映射技术作为网络虚拟化的关键技术,成为学术界与工业界研究的重点之一。针对安全虚拟网络映射中因节点安全感知不全面、匹配不合理导致的映射性能较低问题,文章提出了一种基于熵权折衷排序法(VIKOR)的安全虚拟网络映射算法。该算法首先将安全虚拟网络映射问题构建为混合整数线性规划模型,设计了节点安全优先度指标,实现了虚拟网络节点与底层网络节点安全联合感知;其次在映射过程中综合考虑节点资源属性、拓扑属性和安全属性,采用熵权VIKOR进行节点排序;最后按照节点排序结果依次进行映射,其中链路映射采用k最短路径算法。仿真结果表明,在满足节点各项约束的前提下,文章算法提高了虚拟网络映射成功率和收益开销比。     

基于负载均衡的虚拟网络映射算法研究

为保证虚拟网络请求成功映射,同时不会导致底层网络的部分负载过重,映射性能变差,需要对虚拟网络链路映射进行合理化负载均衡。本文中把虚拟链路带宽资源切片,利用增广子图路径方法选择底层路径,并且将不相交路径资源归一化,设计了基于负载均衡的虚拟网络映射算法。最后,通过仿真将负载均衡算法与路径割裂算法、K最短路径算法进行性能对比。仿真结果表明了负载均衡算法在虚拟网络映射的请求接受率、成本和收益指标方面优于其他两种算法。     

基于拓扑分割与聚类分析的虚拟软件定义网络映射算法

针对目前大部分基于虚拟软件定义网络（vSDN）的映射算法未充分考虑节点与链路之间的相关性的问题,提出了一种基于网络拓扑分割与聚类分析的vSDN映射算法。首先,通过根据最短跳数进行拓扑分割的方法,降低物理网络的复杂度;然后,通过根据节点拓扑和资源属性进行聚类分析的方法,提升映射算法的请求接受率;最后,通过将链路约束分散到节点带宽资源以及节点的度进行约束考量,对不符合链路要求的节点进行重映射,从而优化了节点与链路映射过程。实验结果表明,该算法有效地提升了基于软件定义网络（SDN）架构的虚拟网络映射算法在较低连通概率物理网络下的请求接受率。     

面向动态虚拟网络请求的虚拟网络映射算法

针对虚拟网络请求资源动态变化的实际情况,提出了面向动态虚拟网络请求的虚拟网络映射（DVNR-VNE）算法。以混合线性规划理论为基础,采用多队列的方式分别对不同类型的虚拟网络请求进行预处理,建立了以最小化映射代价和最小迁移代价为优化目标的映射模型,优先映射需要释放资源的请求以获得更多的资源支持其他的虚拟网络,对新到来的虚拟网络请求采用优化后的虚拟网络映射（WD-VNE）算法进行映射。仿真实验表明,该算法降低了链路映射成本和迁移成本并获得了较高的虚拟网络请求接受率。     

基于最优子网的虚拟网络映射算法

针对在虚拟网络映射过程中物理资源碎片化导致嵌入请求被拒绝,从而降低物理资源利用率的问题,提出一种基于最优子网的虚拟网络映射算法,通过优化的重边匹配算法,合并符合约束条件的虚拟节点,同时粗化网络拓扑,运用广度优先搜索算法创建候选物理子网集合,将粗化后的虚拟网络请求映射至最优子网。仿真结果表明,该算法能够减小链路映射跳数,提升虚拟网络请求接受率和收益开销比。     

基于GSA算法的WVN资源映射数学模型

由于传统方法没有从满足成本最小需求角度出发,建立虚拟网络映射目标,导致底层链路利用率较高,剩余带宽较低以及请求接受率不高的问题,于是研究基于GSA算法的无线虚拟网络资源映射数学模型.充分考虑无线虚拟网络资源映射成本、映射收益以及虚拟网络请求接受率建立数学模型,设置节点CPU资源约束、节点映射位置约束、链路带宽资源约束等...     

基于软件定义网络的可靠性虚拟网络映射保障机制

在软件定义网络（SDN）虚拟网络映射中,现有研究者主要考虑请求接受率方面,而忽视了SDN中底层资源失效的问题。为此,针对SDN中可靠性虚拟网络映射（SVNE）问题,提出了一种联合先验式保护和后验式恢复的虚拟网络映射保障机制。首先,在虚拟请求接受之前,对SDN物理网络区域性资源进行感知;然后,采用先验式保护机制为映射域内相对剩余资源变小的虚拟网络元素预留备份物理资源,并将此扩展虚拟网络通过D-ViNE算法映射至物理网络中;最后,在未备份虚拟网络元素发生故障时,采用后验式恢复算法完成故障的恢复,对节点和链路分别采用重映射和重路由的方法完成恢复。实验结果表明,与基于SDN的生存性虚拟网络映射算法（SDN-SVNE）相比,在虚拟请求接受率方面提高了21.9%。另外,该保护机制在虚拟级别故障恢复率、物理级别故障恢复率等方面也具有优势。     

A Global Optimal Mapping Method of Network based on Discrete Optimization Firefly Algorithm

In order to solve the current network rigidity and optimize the resource requirements of multiple virtual networks for synchronous mapping, improve the success rate of virtual network mapping requests, the long-term revenue and overhead ratio of the substrate network, node resource utilization rate and link resource utilization rate. A global optimal mapping method based on discrete optimization firefly algorithm is presented. Analyze the problem of virtual network mapping, map virtual nodes to physical nodes, and map virtual links to physical paths. According to the resource constraints of the virtual network and the substrate network, a multi-objective optimization model of the virtual network mapping is constructed, and the discrete fireflies optimization algorithm is used to obtain the global optimal solution of the virtual network mapping model to achieve the optimal allocation of global resources. The experimental results show that the discrete optimization firefly algorithm has a good performance in solving the virtual network mapping problem, and can effectively improve the virtual network request acceptance rate, node resource utilization rate, link resource utilization rate, and long-term revenue and cost ratio of the substrate network, ensuring Optimization of virtual network resources.     

软件定义承载网中基于负载均衡的虚拟网络重配置方法*

在软件定义承载网(Carrier-SDN)中应用网络虚拟化技术为虚拟网络请求分配资源是解决传统网络结构僵化问题的重要方法之一。针对虚拟网络初次配置产生的瓶颈节点和瓶颈链路造成的底层网络负载不均衡问题,提出一种基于负载均衡的虚拟网络重配置方法(Load Balance Virtual Network Reconfiguration,LB-VNR)。该方法着重设计了虚拟节点的迁移算法、虚拟链路的迁移算法以及重路由映射路径规划算法。仿真结果表明,所提方法在虚拟网络请求接受率、网络收益代价比和虚拟网络负载均衡性方面均具有良好的性能。     

基于改进麻雀搜索算法的服务功能链优化映射算法

为了实现5G网络场景下服务功能链的低成本高效率部署,提出了一种基于改进麻雀搜索算法的服务功能链优化映射算法。在服务功能链映射过程中,采用双层编码方式,将服务请求的组链方案和映射方案进行混合编码,然后使用改进离散麻雀搜索算法进行求解,得到该请求的服务功能链部署方案,并计算其映射权重。当同一时间片内存在多个请求类型时,按照映射权重对所有服务功能链进行排序,优先映射权重高的请求,以此减少延迟开销,提高节点计算资源利用率和链路资源利用率。仿真结果表明,该算法可以有效减少部署开销,提高资源利用率。     

An efficient and coordinated mapping algorithm in virtualized SDN networks

Software-defined networking (SDN) enables the network virtualization through SDN hypervisors to share the underlying physical SDN network among multiple logically isolated virtual SDN networks (vSDNs), each with its own controller. The vSDN embedding, which refers to mapping a number of vSDNs to the same substrate SDN network, is a key problem in the SDN virtualization environment. However, due to the distinctions of the SDN, such as the logically centralized controller and different virtualization technologies, most of the existing embedding algorithms cannot be applied directly to SDN virtualization. In this paper, we consider controller placement and virtual network embedding as a joint vSDN embedding problem, and formulate it into an integer linear programming with objectives of minimizing the embedding cost and the controller-to-switch delay for each vSDN. Moreover, we propose a novel online vSDN embedding algorithm called CO-vSDNE, which consists of a node mapping stage and a link mapping stage. In the node mapping stage, CO-vSDNE maps the controller and the virtual nodes to the substrate nodes on the basis of the controller-to-switch delay and takes into account the subsequent link mapping at the same time. In the link mapping stage, CO-vSDNE adopts the k-shortest path algorithm to map the virtual links. The evaluation results with simulation and Mininet emulation show that the proposed CO-vSDNE not only significantly increases the long-term revenue to the cost ratio and acceptance ratio while guaranteeing low average and maximum controller-to-switch delay, but also achieves good vSDN performance in terms of end-to-end delay and throughput.     

Virtual network mapping algorithm in the cloud infrastructure

Network virtualization has received considerable attention recently because a Cloud Provider (CP) that is responsible for deploying a substrate network in the cloud infrastructure uses network virtualization to support multiple Virtual Network (VN) requests over the shared substrate network. However, mapping multiple VN requests with constraints on virtual nodes and virtual links into a shared substrate network presents a significant challenge, and is considered an NP-hard problem. In this paper, we propose a heuristic mapping algorithm that handles online VN requests. The node mapping algorithm selects a substrate node for mapping that satisfies both a virtual node's resource requirement and its amount of requested bandwidth. The link mapping algorithm either maps a virtual link to the shortest substrate path that satisfies the requested bandwidth of the virtual link or uses the cut-shortest path approach to map a virtual link to multiple substrate paths that satisfy the requested bandwidth of the virtual link. The path migration algorithm migrates virtual links to different substrate paths to maximize the number of accepted VN requests in a substrate network. Simulation results show that the proposed heuristic mapping algorithm uses resources more efficiently, produces more revenue, and has better performance than existing mapping approaches.     

A green energy-aware hybrid virtual network embedding approach

In the past few years, the concept of network virtualization has received significant attention from industry and research fora, as it represents a promising way to diversify existing networks and ensure the co-existence of heterogeneous network architectures on top of shared substrates. Virtual network embedding (VNE) is the process of dynamically mapping virtual resources (i.e. virtual nodes and links) onto physical substrate resources. VNE is the main resource allocation challenge in network virtualization and is considered as an NP-hard problem. Several centralized and distributed VNE approaches have been proposed, with the aim of satisfying different objectives ranging from QoS, to economical profit, and network survivability. More recently, emerging VNE approaches started investigating the optimization of new objectives such as energy-efficiency and networks’ security. In this work, we propose a green energy-aware hybrid VNE hybrid VN embedding approach that aims at achieving energy efficiency and resource consolidation, while minimizing CO₂ emissions resulting from VNs operation. This approach consists of a hierarchical virtual networking management architecture in which control and management nodes collaborate for the splitting and embedding of sub-VNs requests to the cleanest substrate resources (i.e. the resources deployed in a sector with the smallest CO₂ emission factor) available. Three different variants of our VNE algorithms, taking into consideration different resources’ selection criteria (i.e. energy source, request priority, and request location) are presented, and their performance is compared with two existing VNE algorithms based on centralized and distributed embedding approaches. The comparative performance analysis shows that our proposed approach enables a more efficient VN embedding in terms of: a reduced number of substrate resources needed, a faster request mapping time, as well as resource consolidation and reduced resource cost. Furthermore, it enables a reduction of the carbon footprint of the VNE operation, thus resulting in a more green and environmentally conscious approach to network virtualization.     

具有高可靠特征的无线虚拟网络映射方法研究

针对虚拟网络映射过程中链路资源受限和网络生存性问题，分别提出一种基于节点扩展资源的节点映射方案和一种虚拟网络重映射方案。为克服节点映射后链路映射阶段的资源不足问题，通过将节点扩展资源大的节点作为承载节点以确保链路映射的可靠性和高效性，链路映射阶段采用一种基于最小链路代价的映射方案以获得高可靠映射，在此基础上针对网络故障采取一种重映射策略，将失效节点迅速重映射至候选节点集中以确保虚拟网络服务的连续性。通过仿真对几种算法性能进行对比，结果表明所提算法在虚拟网络映射成功率、虚拟网络恢复成功率和资源负载利用率等方面均取得较好结果。