基于节点连通性排序的虚拟网络映射算法

对当今云环境下的数据中心来说,以虚拟资源租赁的运营方式具有极大的灵活性,尤其是以虚拟网络为粒度的资源租赁能够为用户提供更好的个性化需求支持。虚拟网络映射问题是指依据用户资源需求,合理分配底层主机和网络资源。现有的虚拟网络映射算法大多是针对随机拓扑设计的通用算法,未针对数据中心拓扑结构进行优化,映射效率有很大提升空间。针对数据中心的结构特点,提出了一种基于节点连通性排序的虚拟网络映射算法BS-VNE算法。首先,设计了一种最大生成算法来对虚拟节点重要程度进行求解和排序。该算法不仅基于虚拟节点的带宽和连通度,还基于虚拟节点在整个虚拟网络中的连通性来进行节点连通性的计算,以获得更加合理的排序结果。然后,根据虚拟节点连通性排序结果利用离散粒子群优化算法求解虚拟网络的映射解。在求解过程中,引入了针对数据中心结构的物理网络拓扑启发式规则,并将其组合到粒子搜索过程中,以提高映射算法的收敛速度。仿真实验结果表明,与现有算法相比,本文提出的算法可以提高物理网络的收益/成本比和资源利用率。     

基于混合群智能优化的虚拟网络映射算法

网络虚拟化是突破网络发展僵局的一项重要技术,而虚拟网络映射(VNE)是网络虚拟化的一个主要问题。提高底层网络资源的利用率和收益是虚拟网络映射的主要目标。针对底层网络支持路径分裂的情况,建立了整数线性规划(ILP)模型,并提出基于混合群智能优化的虚拟网络映射算法。该算法在兼顾映射开销和映射均衡性的基础上利用粒子群优化算法(PSO)和遗传算法(GA)迭代优化映射方案。仿真实验结果表明,与现有的主流研究成果相比,该算法显著地提高了底层网络长期平均运营收益与虚拟网络请求接受率。     

一种基于约束优化的虚拟网络映射方法

虚拟网络映射问题将不同的虚拟网络应用映射到相同的基础设施网络中,这是一个极具挑战性的问题.针对该问题,提出了一种基于约束优化的虚拟网络映射方法,将映射问题分解为节点映射和链路映射两个阶段,其中,前者是将虚拟节点映射到物理节点上,后者将虚拟链路映射到物理路径上,它们都是NP难问题.针对节点映射和链路映射分别提出了node-mapping算法和link-mapping算法.node-mapping算法基于贪婪算法的思想,映射时考虑了物理节点所能提供的资源数量以及物理节点间距离两个因素,该算法能够保证基础设施网络中各节点间的负载相对均衡;同时,通过采用访问控制机制,过滤一些异常的虚拟网络请求,能够有效地提高资源的使用效率.link-mapping算法基于人工智能领域中的分布式约束优化思想,其能够保证得到的解是全局最优的,即映射链路的代价最小.最后,通过模拟实验对该方法进行验证,实验结果表明该方法在求解虚拟网络映射问题时的性能良好.     

无线多媒体传感器网络中的覆盖增强算法

针对无线多媒体传感器网络节点感知范围的视角性和方向性,提出了基于虚拟力和粒子群算法的覆盖增强算法.该算法通过传感器节点之间存在着的大小不等的引力或者斥力的虚拟力作用,调整传感器节点的位置,使网络中节点的分布合理和均匀;通过粒子群优化算法调整有向传感器节点的工作方向以达到覆盖的最大化.仿真实验结果表明,基于虚拟力和粒子群算法的覆盖增强算法能很好的提高网络的覆盖率.     

一种虚拟路由器资源映射算法研究

网络虚拟化技术的提出,为解决互联网"僵化"问题找到了新的思路,受到广泛的关注。在虚拟路由器平台中,若干台互联的网络服务器资源组成了底层物理网络,通过虚拟网络映射技术,将物理网络资源有效地映射到虚拟网络设备上,组成多个虚拟网络,满足用户对网络的多样化需求。虚拟路由器资源映射问题是虚拟网络映射问题的基础,虚拟路由器实例与物理资源的映射方法决定了虚拟网络平台资源的利用率和虚拟网络系统的性能。针对虚拟路由器平台资源分配的问题,提出了物理网络资源模型和虚拟路由器资源请求模型,设计了一种启发式虚拟路由资源分配算法,并对算法的复杂性和优化目标进行了分析。     

5G网络切片中基于离散粒子群和Kruskal算法的跨域虚拟网络映射

5G移动通信网将租用多个基础设施提供商的数据中心等资源共同合作构建网络切片,针对如何高效地进行跨域虚拟网络映射这一网络切片全生命周期管理中的关键问题,提出一种两阶段的跨域映射策略DPSO-K。首先基于资源竞价统筹考虑节点资源和域间带宽资源,然后提出基于优化离散粒子群算法的跨域虚拟网络映射,可以有效提高寻优能力;对于开销相对较小的域内映射来说,提出一种基于Kruskal最小生成树的快速算法,旨在缩短切片实例化时间,减小业务上线速度。相比于传统先进行虚拟网络映射划分请求再统一映射链路的方法,该策略在划分请求中考虑域间带宽开销,在映射链路中关注重点链路的映射,采用集中管理、分布控制的方式实现物理网络资源的有效利用。实验结果表明该算法能够以更小的额外开销、更短的划分时间实现更高的接受率。     

基于多目标粒子群优化的虚拟网络映射算法

在虚拟网络映射中,多数研究只考虑一个映射目标,不能体现多方的利益。为此,将多目标算法和粒子群算法结合,提出了一种基于多目标粒子群优化（PSO）的虚拟网络映射算法（VNE-MOPSO）。首先,在基本的粒子群算法中引入交叉算子,扩大了种群优化的搜索空间;其次,在多目标优化算法中引入非支配排序、拥挤距离排序,从而加快种群的收敛;最后,以同时最小化成本和节点负载均衡度为虚拟网络映射目标函数,采用多目标粒子群优化算法求解虚拟网络映射问题（VNMP）。实验结果表明,采用该算法求解虚拟网络映射问题,在网络请求接受率、平均成本、平均节点负载均衡度、基础设施提供商的收益等方面具有优势。     

基于元胞遗传机制的虚拟网络映射算法

满足节点和链路约束条件的虚拟网络请求最优映射问题是NP-难问题,粒子群算法和遗传算法等启发式算法是解决这类问题的主要手段。这类启发式算法从数学模型优化的角度来求解问题,但未考虑虚拟网络映射节点本身的变化对最优解的影响,存在收敛速度较慢和容易陷入局部最优解的问题。文中将元胞遗传机制引入虚拟网络映射问题中,提出了虚拟网络映射算法VNE-CGA。该算法利用元胞自动机对节点建模,使用“B4567/S1234”规则来替代传统遗传算法中的交叉操作;通过对邻居的学习来指导个体的寻优过程,弥补了传统遗传算法的固有缺陷,最终提高了虚拟网络请求的接受率以及底层物理网络的运营收益。     

基于云网络架构的虚拟网络映射算法研究

云网络架构采用控制与转发分离机制实现了资源的灵活分配,为了满足云网络架构的资源分配符合多业务的资源需求,提出了一种基于云网络架构的虚拟网络映射算法,提高了资源利用率。建立的虚拟网络映射算法模型,给出了虚拟网络映射算法的约束条件和优化目标。针对语音、视频和数据3种业务进行了仿真,结果表明,提出的算法提高了控制资源利用率、转发资源利用率和链路资源利用率。     

基于资源拆分的虚拟网络功能服务链映射算法

针对网络虚拟化环境下虚拟网络功能服务链的资源分配以及部署问题,提出了基于资源拆分的虚拟网络功能服务链部署策略。通过对租户的资源需求进行主动拆分,利用更小的资源分配粒度达到提高物理资源利用率的目的。利用最优化理论将虚拟网络功能服务链的资源分配问题建模成具有链式拓扑结构的虚拟网络映射问题,并通过设计高效的启发式算法以有效地解决这一问题。实验结果表明,该算法与其它虚拟网络映射算法相比,能有效提高物理资源的利用率以及租户请求的接收率。     

Performance evaluation of artificial intelligence algorithms for virtual network embedding

Network virtualization is not only regarded as a promising technology to create an ecosystem for cloud computing applications, but also considered a promising technology for the future Internet. One of the most important issues in network virtualization is the virtual network embedding (VNE) problem, which deals with the embedding of virtual network (VN) requests in an underlying physical (substrate network) infrastructure. When both the node and link constraints are considered, the VN embedding problem is NP-hard, even in an offline situation. Some Artificial Intelligence (AI) techniques have been applied to the VNE algorithm design and displayed their abilities. This paper aims to compare the computational effectiveness and efficiency of different AI techniques for handling the cost-aware VNE problem. We first propose two kinds of VNE algorithms, based on Ant Colony Optimization and genetic algorithm. Then we carry out extensive simulations to compare the proposed VNE algorithms with the existing AI-based VNE algorithms in terms of the VN Acceptance Ratio, the long-term revenue of the service provider, and the VN embedding cost.     

COVE: Co-operative Virtual Network Embedding for Network Virtualization

Network virtualization provides a promising solution for next-generation network management by allowing multiple isolated and heterogeneous virtual networks to coexist and run on a shared substrate network. A long-standing challenge in network virtualization is how to effectively and efficiently map these virtual nodes and links of heterogeneous virtual networks onto specific nodes and links of the shared substrate network, known as the Virtual Network Embedding (VNE) problem. Existing centralized VNE algorithms and distributed VNE algorithms both have advantages and disadvantages. In this paper, a novel cooperative VNE algorithm is proposed to coordinate centralized and distributed algorithms and unite their respective advantages and specialties. By leveraging the learning technology and topology decomposition, autonomous substrate nodes entrusted with detailed mapping solutions cooperate closely with the central controller with a global view and in charge of general management to achieve a successful embedding process. Besides a topology-aware resource evaluation mechanism and customized mapping management policies, Bloom filter is elaborately introduced to synchronize the mapping information within the substrate network, instead of flooding which generates massive communication overhead. Extensive simulations demonstrate that the proposed cooperative algorithm has acceptable and even better performance in terms of long-term average revenue and acceptance ratio than previous algorithms.     

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.     

基于负载均衡的无线虚拟网络映射算法

针对网络僵化的问题,目前多采用网络虚拟化（NV）方法进行解决,其关键技术是虚拟网络映射（VNE）。为解决无线VNE过程中功率和带宽资源使用不均衡的问题,基于负载均衡原理提出一种联合资源分级的无线VNE算法。首先,采用新的节点资源排序方式,其中将节点功率和平均链路带宽作为排序依据;其次,对资源进行分级,以动态调整虚拟网络请求对功率和带宽资源的需求;最后,改进功率和带宽资源的单位成本,并以最小化成本为目标函数选择资源分配方案。与原有的无线VNE算法WVNE-JBP相比,所提算法的总体接受率提高了11.7个百分点,平均功率利用率提高了4.4个百分点,平均带宽利用率提高了1.6个百分点。实验结果表明,所提算法能有效提高虚拟网络接受率和资源利用率。     

An evaluation method for secure virtual network embedding algorithms

Due to the ossification of the current Internet, it is difficult to launch new service. One of solutions is network virtualization. Numerous virtual network embedding (VNE) algorithms have been proposed in many literatures. But, there is no general methods or frameworks for evaluation of these algorithms. We have analyzed a number of studies, and found appropriate evaluation indexes that can be used in evaluating the functionalities of VNE algorithms. Based on those indexes, we presented a new evaluation method of secure VNE algorithms. To make a virtual network with the various requirements, the infrastructure provider needs effective resource allocation algorithm. The role of VNE is to allocate physical resources to virtual nodes or links to form virtual networks. In order to use the resources of physical networks, appropriate resource allocation algorithms are required. We found a set of evaluation indexes by analyzing the previous proposed researches. Through analysis, we found that our proposed method can be grouped into two functional attributes for classification. One attribute is the basic attributes that mean special features of architecture and the other is the evaluation attributes that perform the assessment of algorithms. We have evaluated the algorithms with our proposed evaluation methods and found to be useful to choose the appropriate algorithm to the infrastructure provider. The proposed method was found to be more convenient to perform the evaluation of the algorithms in real-world simulation. This method helps infrastructure providers to choose the appropriate VNE algorithm.     

LIVE: Learning and Inference for Virtual Network Embedding

Network virtualization provides a promising tool for next-generation network management by allowing multiple heterogeneous virtual networks to run on a shared substrate network. A long-standing challenge in network virtualization is how to effectively map these virtual networks onto the shared substrate network, known as the virtual network embedding (VNE) problem. Most heuristic VNE algorithms find practical solutions by leveraging a greedy matching strategy in node mapping. However, greedy node mapping may lead to unnecessary bandwidth consumption and increased network fragmentation because it ignores the relationships between the mapped virtual network requests and the mapping ones. In this paper, we re-visit the VNE problem from a statistical perspective and explore the potential dependencies between every two substrate nodes. We define a well-designed dependency matrix that represents the importance of substrate nodes and the topological relationships between them, i.e., every substrate node’s degree of belief. Based on the dependency matrix generated from collecting and processing records of accepted virtual network requests, Bayesian inference is leveraged to iteratively select the most suitable substrate nodes and realize our novel statistical VNE algorithm consisting of a learning stage and an inference stage in node mapping. Due to the overall consideration of the relationships between the mapped nodes and the mapping ones, our statistical approach reduces unnecessary bandwidth consumption and achieves a better performance of embedding. Extensive simulations demonstrate that our algorithm significantly improves the long-term average revenue, acceptance ratio, and revenue/cost ratio compared to previous algorithms.     

Greener networking in a network virtualization environment

Energy consumption of network operators can be minimized by the dynamic and smart relocation of networking resources. In this paper, we propose to take advantage of network virtualization to enable a smart energy aware network provisioning. The virtualization of networking resources leads to the problem of mapping virtual demands to physical resources, known as Virtual Network Embedding (VNE). Our proposal modifies and improves exact existing energy aware VNE proposals where the objective is to switch off as many network nodes and interfaces as possible by allocating the virtual demands to a consolidated subset of active physical networking equipment. As exact energy efficient VNE approaches are hard to solve for large network sizes and have an adverse effect in the number of successful embeddings, an heuristic approach to reconfigure the allocation of already embedded virtual networks, minimizing the energy consumption, is also proposed.