Network virtualization over WDM and flexible-grid optical networks

Network virtualization can eradicate the ossification of the Internet and stimulate innovation of new network architectures and applications. Optical networks are ideal substrates for provisioning high-bandwidth virtual-network services. In this study, we investigate the problem of network virtualization over both WDM and flexible-grid optical networks by formulating the problems as mixed integer linear programs (MILP). Two heuristics, namely MaxMapping and MinMapping, are developed for each kind of network to solve the problem quickly but suboptimally. Numerical examples show that MinMapping consumes fewer spectrum resources than MaxMapping and performs very close to the optimal results derived by the MILP in both kinds of optical networks, by exploring the opportunities of traffic grooming. Also, it is verified that flexible-grid optical networks can be more spectrum efficient than WDM networks as the substrate for network virtualization.     

Power-aware virtual optical network provisioning in flexible bandwidth optical networks [Invited]

Considering the virtual network infrastructure as a service, optical network virtualization can facilitate the physical infrastructure sharing among different clients and applications that require optical network resources. Obviously, mapping multiple virtual network infrastructures onto the same physical network infrastructure is one of the greatest challenges related to optical network virtualization in flexible bandwidth optical networks. In order to efficiently address the virtual optical network (VON) provisioning problem, we can first obtain the virtual links’ order and the virtual nodes’ order based on their characteristics, such as the bandwidth requirement on virtual links and computing resources on virtual nodes. We then preconfigure the primary and backup paths for all node-pairs in the physical optical network, and the auxiliary graph is constructed by preconfiguring primary and backup paths. Two VON mapping approaches that include the power-aware virtual-links mapping (PVLM) approach and the power-aware virtual-nodes mapping (PVNM) approach are developed to reduce power consumption for a given set of VONs in flexible bandwidth optical networks with the distributed data centers. Simulation results show that our proposed PVLM approach can greatly reduce power consumption and save spectrum resources compared to the PVNM approach for the single-line rate and the mixed-line rate in flexible bandwidth optical networks with the distributed data centers.     

Virtual infrastructure mapping in software-defined elastic optical networks

Software-defined networking (SDN) enables efficient and scalable network virtualization, which allows infrastructure resources such as computing and networking resources to be abstracted and outsourced as a service. The SDN technologies can be extended to the optical transport networks to achieve an intelligent and flexible resource management, thus achieving high-capacity, low-cost, and long-reach optical transport networks. In this paper, we introduce an architecture for software-defined elastic optical networks and study the virtual infrastructure (VI) mapping problem with the objective of minimizing the blocking probability. We propose a set of efficient heuristic algorithms, among which the Network followed by Compute Load Balancing (NCLB) algorithm is a novel attempt to solve the VI mapping problem by provisioning the networking resource first followed by allocating the computing resource. Furthermore, we propose a modified version of NCLB, called Network Depth-based NCLB (ND-NCLB), which confines the VI mapping assignment in a small-range sub-network to further optimize the physical network resource consumption. Through comprehensive simulations in various scenarios, we demonstrate that the proposed ND-NCLB algorithm achieves the best performance in terms of blocking probability compared to the other algorithms in this work.     

Virtual network embedding in software-defined hybrid networks

Network virtualization provides a powerful way of sharing substrate networks. Efficient allocation of network resources for multiple virtual networks (VNs) has always been a challenging task. In particular, with the demands of the customized VN requests are increasing, many problems arise as network conditions change dynamically. Especially, when the resources conflicting appear during the lifetime of VNs, it needs service provider (SP) to provide a fast and effective solution. Recently, software defined network (SDN) has emerged as a new networking paradigm, SDN’s centralized control and customizable routing features present new opportunities for convenient and flexible embedding VNs in the network. However, due to the limitations of the SDN, in the short term, replacing all legacy devices in current operational networks by SDN-enabled switches is impractical. Thus, in our study, we focus on the scenario of VN embedding (VNE) in software-defined hybrid networks. In this work, first of all, we propose partially deploying SDN nodes, and then, we use the characteristics of SDN to allocate resources for VN requests, and redirect the path for requests conflict in hybrid SDN network. We formulate the problems and provide simple algorithms to solve them. Simulation results show that our scheme is high responsiveness and acceptance ratio.     

基于多商品流模型的虚拟链路映射

网络虚拟化是解决网络僵化问题和更好地共享底层网络资源的一种有效途径,虚拟网络映射是实施网络虚拟化的关键问题之～。虚拟网络映射包括节点映射和链路映射两个方面,其目标是为虚拟网络请求分配合适的底层网络节点和链路资源。阐述了底层网络支持路径分割时,如何基于多商品流模型实现VN链路映射。     

Optimal mapping of virtual networks with hidden hops

Network virtualization has emerged as a solution for the Internet inability to address the required challenges caused by the lack of coordination among Internet service providers for the deployment of new services. The allocation of resources is one of the main problems in network virtualization, mainly in the mapping of virtual nodes and links to specific substrate nodes and paths, also known as the virtual network embedding problem. This paper proposes an algorithm based on optimization theory, to map the virtual links and nodes requiring a specific demand, looking for the maximization of the spare bandwidth and spare CPU in the substrate network, taking into account the CPU demanded by the hidden hops when a virtual link is mapped. The components of the virtual networks (nodes and links) that do not ask for an specific demand are then allocated following a fairness criteria.     

Adaptive scheme based on status feedback for virtual network mapping

Network virtualization is considered as a powerful way to deploy different network architectures and protocols over a shared physical infrastructure.Virtual network(VN)embedding plays an important role in the network virtualization environment.Virtual network embedding is mainly about mapping virtual nodes and virtual links onto the physical network resources efficiently.However,load balancing of substrate network has not received much consideration.This paper proposes an adaptive virtual network mapping algorithm based on status feedback.The main contribution is to embed the virtual network requests according to the current load distribution of substrate network.This adaptive algorithm differentiates the residual bandwidth of substrate links and takes full advantage of the multi-path to improve the load balancing of the substrate network.Simulation experiments show that the proposed algorithm improves the load distribution of substrate network distinctly while reducing the average substrate link stress significantly.     

基于节点可靠性感知和共享路径保护的虚拟网映射算法研究

网络虚拟化技术为目前的网络架构提供了一种有效的扩展手段。近年来,底层网络基础设施失效事件频发,因此如何提高虚拟网络的可靠性成为目前该领域一个研究热点。对在保证虚拟网络可靠性的同时如何最小化底层网络映射开销问题进行研究,设计了一个新的启发式算法对其进行求解。实验表明,相比其他算法,所提算法网络带宽资源开销更低。     

Exploring online virtual networks mapping with stochastic bandwidth demand in multi-datacenter

Network virtualization serves as a promising technique for providing a flexible and highly adaptable shared substrate network to satisfy the diversity of demands and overcoming the ossification of Internet infrastructure. As a key issue of constructing a virtual network (VN), various state-of-the-art algorithms have been proposed in many research works for addressing the VN mapping problem. However, these traditional works are efficient for mapping VN which with deterministic amount of network resources required, they even deal with the dynamic resource demand by using over-provisioning. These approaches are obviously not advisable, since the network resources are becoming more and more scarce. In this paper, we investigate the online stochastic VN mapping (StoVNM) problem, in which the VNs are generated as a Poisson process and each bandwidth demand x _i follows a normal distribution, i.e., x _i ~ N(μ _i , σ _i ²). Firstly, we formulate the model for StoVNM problem by mixed integer linear programming, which with objective including minimum-mapping-cost and load balance. Then, we devise a sliding window approach-based heuristic algorithm w-StoVNM for tackling this NP-hard StoVNM problem efficiently. The experimental results achieved from extensive simulation experiments demonstrate the effectiveness of the proposed approach and superiority than traditional solutions for VN mapping in terms of VN mapping cost, blocking ratio, and total net revenue in the long term.     

Dynamic recovery for survivable virtual network embedding

Network virtualization is a promising way to overcome the current ossification of the Intemet. It is essential challenge to find effective, efficient and robust embedding algorithms for recovering virtual network. The virtual network mapping algorithm based on integer programming which was proposed months ago. But it did consider the faults of physical network resources, which is so called survivable virtual network embedding （VNE） problem. Previous strategies for enabling survivability in network virtualization focused on providing protection for the physical network or enhancing the virtual networks by providing backup physical resources in advance, and treated all the physical failures as link failures. In the article, a dynamic recovery method is proposed to solve the survivable virtual network embedding problem based on the integer programming VNE algorithm. The dynamic recovery method doesn＇t need to backup physical resources and it makes more substrate resources which can be used in the embedding. The dynamic recovery process will be activated only when physical failures occur. Different algorithms are used to recovery node and link failures. Simulations show that the method helps to recover almost all of physical failures by finding the substitute nodes and paths, and its performance is very close to that of pure VNE method without considering physical failures.     

基于虚拟化的无线网络规划优化平台的研究

研究一种基于虚拟化的无线网络规划优化平台。通过虚拟化技术,该平台能够集成各种无线网络规划优化软件工具,不仅保留了传统单机版软件工具使用灵活方便的优点,同时提供了集中管理、多方式远程访问、扩展性强、硬件资源按需分配以及高效率、大规模仿真的需求。介绍了平台的总体设计方案以及网络与虚拟化设计方案。对平台的使用进行了展示。     

信任感知的安全虚拟网络映射算法

针对网络虚拟化技术带来的新的安全威胁,将信任关系和信任度引入到虚拟网络资源分配中,量化分析了网络虚拟化环境中的安全问题,构建了安全虚拟网络映射的数学模型,并在映射过程中考虑节点的局部和全局重要性,采用逼近理想排序法方法对节点进行多属性重要度排序,提出了一种信任感知的安全虚拟网络映射算法。仿真结果表明,该算法在满足虚拟网络请求可信需求的条件下,获得了较好的映射成功率、映射收益和资源利用率。     

Virtual access network embedding in wireless mesh networks

Network virtualization of a wireless mesh network (WMN) is an economical way for different subscribers to customize their exclusive access networks through a common network infrastructure. The most critical task of network virtualization is virtual network embedding, which can be divided into two sub-problems: node mapping and link mapping. Although there exist approaches to virtual network embedding in wired networks, the characteristics of WMNs make virtual network embedding become a unique and challenging problem. In this paper, virtual access network embedding is studied for WMNs. To support flexible resource allocation in virtual access network embedding, each access node is designed based on orthogonal frequency division multiple access (OFDMA) dual-radio architecture. Through subcarrier allocation on each link, virtual access networks are gracefully separated from each other. To coordinate channel assignment across different links under the constraint of a limited number of orthogonal channels, a novel channel allocation algorithm is proposed to exploit partially-overlapped channels to improve resource utilization. Since the virtual access network embedding problem is NP-hard, a heuristic algorithm is developed based on an enhanced genetic algorithm to obtain an approximate but effective solution. Simulation results illustrate that the virtual access network embedding framework developed in this paper works effectively in WMNs.     

Fault-tolerant monitor placement for out-of-band wireless sensor network monitoring

Monitoring a sensor network to quickly detect faults is important for maintaining the health of the network. Out-of-band monitoring, i.e., deploying dedicated monitors and transmitting monitoring traffic using a separate channel, does not require instrumenting sensor nodes, and hence is flexible (can be added on top of any application) and energy conserving (not consuming resources of the sensor nodes). In this paper, we study fault-tolerant out-of-band monitoring for wireless sensor networks. Our goal is to place a minimum number of monitors in a sensor network so that all sensor nodes are monitored by k distinct monitors, and each monitor serves no more than w sensor nodes. We prove that this problem is NP-hard. For small-scale network, we formulate the problem as an Integer Linear Programming (ILP) problem, and obtain the optimal solution. For large-scale network, the ILP is not applicable, and we propose two algorithms to solve it. The first one is a ln(kn) approximation algorithm, where n is the number of sensor nodes. The second is a simple heuristic scheme that has much shorter running time. We evaluate our algorithms using extensive simulation. In small-scale networks, the latter two algorithms provide results close to the optimal solution from the ILP for relatively dense networks. In large-scale networks, the performance of these two algorithms are similar, and for relatively dense networks, the number of monitors required by both algorithms is close to a lower bound.     

Reliability- and performance-driven mapping for regular 3D NoCs using a novel latency model and Simulated Allocation

Network-on-Chip (NoC) -based communication architecture is promising in addressing the communication bottlenecks in current and future multicore processors. In this work, we consider the application-specific mapping problem and electromigration (EM) -induced through-silicon via (TSV) reliability issue in tile-based three-dimension (3D) NoC architectures. In 3D NoCs, network contention may result in unacceptable communication delay among the processing cores and thus has significant effect on the system performance. So we propose a new latency model for the routers which characterizes the network contentions among different traffic flows from sharing of network resources. Then we solve the core mapping problem by a fast while efficient stochastic algorithm called Simulated Allocation (SAL), which integrates our new latency model and also aims to optimize the communication power, latency in the mapping procedure. After that, we use an incremental method to optimize the reliability of the TSVs. Experimental results show that, contention-aware model (CAM) has 25% larger network latency than our latency model; compared with particle swarm optimization (PSO), our SAL algorithm can achieve 7% less power with about 7.5 × run-time speedup; as for reliability, our method can achieve better results (up to 10 × increase in terms of the void nucleation time (VNT)) with 7.64% increased latency.     

面向SDN网络虚拟化平台的控制器放置算法

随着网络技术发展,以网络虚拟化为手段解决TCP/IP网络体系结构僵化问题已成为未来网络领域发展的主流方向之一.SDN(software defined networking,软件定义网络)作为一种新兴的网络体系结构,为网络虚拟化提供了有效的解决方案.首先总结了当前具有代表性的SDN网络虚拟化平台,并对比了SDN与传统网络环境中部署虚拟网的区别,然后针对SDN网络虚拟化平台中的虚拟网络映射问题,提出一种时延敏感的虚拟化控制器放置算法,最后通过实验验证了该算法在提高网络资源的利用效率的同时,保证了控制器与底层交换机的通信时延在可接受范围之内.     

未来网络虚拟化关键技术研究

网络虚拟化可使得多个服务提供商动态组合多个异构的共存却相互隔离的虚拟网。文章提出一种支持上下文感知的网络虚拟化实现方法,通过虚拟化网络资源和动态资源分配与控制技术建立底层资源与上层服务之间的映射关系,通过虚拟化层在应用层和底层基础网络间形成透明的隔离,同时采用认知管理的方式对虚拟化网络进行动态控制,以改善和提升互联网能力,满足端对端服务质量、安全性、可管理性等需求。     

Hop-Limit Path Mapping Algorithm for Virtual Network Embedding

Virtual network (VN) mapping which deals with the allocation of network resources from the shared physical substrate to individual VNs is one of the key challenges for the application of realizing network virtualization. While a variety of state-of-the-art algorithms have attempted to address this issue from different aspects, the challenge still remains for mapping virtual link with hop count constraint. This paper presents a fast approximation path mapping algorithm to address this issue by formulating such virtual link mapping problem as a path-flow mathematical programming model, which aims to minimize the maximum link load factor. Through the use of the primal–dual method, a fully polynomial time approximation algorithm is proposed to solve this model. The experimental results show that the proposed algorithm can effectively solve the problem of path mapping with hop limit.     

无线网络虚拟化中资源共享的功率分配算法

针对传统无线网络中功率不能动态分配共享的问题,采用无线网络虚拟化,设计了一种基于博弈的两阶段功率分配方法(G2SPA, game theory based two steps power allocation scheme for wireless network virtualization),首先利用买卖博弈模拟了服务提供商(SP, service provide)和移动用户(MUE, mobile user equipment)之间的相互影响,提出了基于斯坦博格均衡(SE, stackelberg equilibrium)的报价策略。然后,利用拍卖理论对空闲下行功率资源进行再分配,采取McAfee机制保证拍卖的诚实性。通过仿真实验证明G2SPA算法的正确性和有效性。     

A model for virtual network embedding using Artificial Bee Colony

In a network virtualization environment, a significant research problem is that of virtual network embedding. As the network virtualization system is distributed in nature, an effective solution on how to optimally embed a dynamically generated virtual network request on the substrate networks that are owned and managed by multiple infrastructure providers needs proper attention. The problem is computationally hard, and therefore, many approaches, implying heuristics/meta‐heuristics, have been applied for the same. A meta‐heuristic, Artificial Bee Colony algorithm is getting popular due to its robustness toward complex problem solving. A novel approach based on Artificial Bee Colony to address the dynamic virtual network embedding problem in a multiple infrastructure provider scenario is proposed in this work. Bee population is initialized by using a greedy heuristic in which the number of substrate networks together with virtual network requests constructs a bee. Generated solution, in the population, is improvised by using greedy selection that explores a local search method adopted by the bees. In greedy selection, the new candidate source is memorized by the bee if its fitness is better than the fitness of the existing source. The performance study of the proposed model is done by simulation over various metrics such as embedding cost, embedding time, and acceptance ratio. A comparative study is conducted with other nature‐inspired virtual network embedding algorithms on these metrics. The findings affirm that the proposed virtual network embedding approach performs well and produces better results.