Dynamic transparent virtual network embedding over elastic optical infrastructures

Aiming at the virtual network embedding problem under dynamic service request, Service Request Aware-based Dynamic Virtual Network Embedding (SRAD) algorithm is proposed. We first present virtual network embedding model, and then define virtual network construction cost according to the dynamic characteristic of service request. Our goal is to find the optimal reconfiguration policies by awaring service request type and changing trends, which can minimize the overall construction cost using substrate resource. Experimental results show that the proposed algorithm satisfies the service request, achieves higher success ratio and gains higher revenue/cost ratio for substrate network comparing with the existing algorithms.

Recently network virtualization has been proposed as a promising way to overcome the current ossification of the Internet by allowing multiple heterogeneous virtual networks (VNs) to coexist on a shared infrastructure. A major challenge in this respect is the VN embedding problem that deals with efficient mapping of virtual nodes and virtual links onto the substrate network resources. Since this problem is known to be NP-hard, previous research focused on designing heuristic-based algorithms which had clear separation between the node mapping and the link mapping phases. This paper proposes VN embedding algorithms with better coordination between the two phases. We formulate the VN embedding problem as a mixed integer program through substrate network augmentation. We then relax the integer constraints to obtain a linear program, and devise two VN embedding algorithms D-ViNE and R-ViNE using deterministic and randomized rounding techniques, respectively. Simulation experiments show that the proposed algorithms increase the acceptance ratio and the revenue while decreasing the cost incurred by the substrate network in the long run.

The main resource allocation research challenge in network virtualization is the Virtual Network Embedding (VNE) Problem. It consists of two stages, usually performed separately: node mapping and link mapping. A new mathematical multi-constraint routing framework for linear and non-linear metrics called “paths algebra” has already been proposed to solve the second stage, providing good results thanks to its flexibility. Unlike existing approaches, paths algebra is able to include any kind of network parameters (linear and non-linear) to solve VNE in reasonable runtime. While paths algebra had only been used to solve one stage (link mapping) of the VNE, this paper suggests an improvement to solve VNE using the paths algebra-based strategy by coordinating, in a single stage, the mapping of nodes and links based on a ranking made of the bi-directional pair of nodes of the substrate network, ordered by their available resources. Simulation results show that the New Paths Algebra-based strategy shows significant performance improvements when compared against the uncoordinated paths Algebra-based link mapping approach.

With the emergence of cloud services based on data centers, demands for bandwidth-intensive applications have increased dramatically, and application services have transferred to a more diversified direction. Management as well as capacity of the backbone network needs further development to catch up with rapidly evolved application demands. Optical network virtualization can facilitate the sharing of physical infrastructure among multiple network applications. Virtual Network Embedding (VNE), the main implementation of network virtualization, determines how to map a virtual network request onto physical substrate. To expand the network capacity, flexible-grid elastic optical networks have been considered as a promising supporting technology for the future infrastructure of the next-generation Internet. However, due to the expense of key enabling equipment for flexible grid optical networks, the brown-field migration from a fixed grid to a flexible grid gave birth to the co-existing fixed/flexible grid. Based on the co-existing fixed/flexible grid optical networks, we investigate the problem of Virtual Optical Network (VON) provisioning, and present a flexible-grid-aware virtual network embedding algorithm to map the virtual networks onto the substrate network. In addition, the performance of the algorithm was evaluated under four different network scenarios. Simulation results show that the proposed algorithm can achieve better performance in all four scenarios.

A major challenge in virtual network embedding is to find an efficient mapping of each virtual network (VN) to the nodes and links in the substrate network (SN) so that the residual SN can host as many VN requests as possible. This network optimization problem has been shown to be NP hard. In this paper we propose a “border matching” mechanism in VN embedding, which is shown to outperform a number of existing VN embedding algorithms. In particular, we devise an iterative algorithm called “VNE-B”. Typical VN embedding algorithms may cause fragmentations of the substrate network, i.e. the substrate resources are fragmented into small isolated pieces, making it unable to meet larger future VN requests. VNE-B starts the mapping from the “border” nodes of both VNs and the SN for reducing fragmentation of SN resources. Our experimental evaluations show that VN embedding algorithms with VNE-B result in more efficient mappings and thus fewer rejections for VN requests. We also visualize the residual SN to demonstrate the effectiveness of VNE-B.

Green virtual network embedding with supervised self-organizing map

This paper explores the most urgent task to initialize a virtual network in the network virtualization environment, which always called the virtual network embedding. Different to the previous works to take the embedding process as two steps: node mapping stage and then edge mapping stage, this paper contribute to solve these processes all in one discrete nonlinear combined optimization. Based on modeling the virtual network (VN) request and substrate network (SN), this paper proposed mathematical description to the embedding process which building the relationship between node mapping and edge mapping stages. After that, a virtual network embedding cost is introduced as an objective function, and then the virtual network embedding can be concluding to minimize the objective cost as a mathematical programming problem. The obtained programming results in LINGO9.0 show that the proposed method can finish a virtual network embedding by mathematical programming in one step.

Optical network virtualisation has recently become a hot topic among the research community due to its potential to enable the shaping of the Infrastructure as a Service (IaaS) concept. A major challenge that arises of paramount importance when virtualising a network is the so called Virtual Network (VN) embedding problem. While this problem has been extensively treated for electrical networks, there is very little work regarding Virtual Optical Network (VONs) embedding. This paper addresses the VON embedding problem, giving an insight about the potential challenges and presenting solutions that allow to optimally solving this problem in dynamic network scenarios.

Network virtualization is widely considered to be one of the main paradigms to solve the Internet ossification problem. One of the most challenging works in this paradigm will be the efficient use of the substrate resources, which is known as virtual network embedding (VNE) problem. The VNE problem is known to be an NP-hard problem which needs some heuristic and approximate algorithms to be solved. In this paper, the VNE is decomposed into two stages: virtual node and virtual link mapping. In the node mapping stage, the breadth first search algorithm is employed to construct loop-free tree for each substrate node, then we explored different hops sufficient capacity of each SN node via the loop-free tree, and analyze the best value of hops that contributes to gain better performance for the algorithm. And the link mapping stage, it can be seen as multi-constraint routing, which is known to be an NP-hard problem. The paths algebra framework was adopted to address this problem, for its convergence for multi-constraint routing problem and a large solution space that the algorithm can gain an enhanced optimization performance.

Virtual network embedding (VNE) refers to allocating reasonable substrate network resources for virtual network (VN) requests that include computing resources and network resources, so as to obtain optimal income from leasing virtual resources. Such a way of providing virtual resources is the key technology of cloud computing and can greatly save the operating cost of enterprises and provide flexibility of application deployment. However, the existing VNE algorithms are mostly oriented to traditional stochastic network topologies. Due to the high connectivity and server density of data centers and the complexity of the user’s resource requirements, the traditional VNE algorithms suffer from low resource utilization rate and revenues in the VNE on the data centers. Different from the existing algorithms which are often based on heuristic algorithms, this paper proposes a VNE algorithm for data center topology based on the Q-learning algorithm which is a typical reinforcement learning method. The algorithm an agent for each VN designs a reward function related to the effect of virtual link embedding, which is used to update the Q-matrix through unsupervised learning process. Then, the agent can find the optimal embedding strategy based on the Q-table from each learning. Simulation results demonstrate that the proposed algorithm can improve the resource utilization ratio and obtain a better revenue/cost ratio of the substrate network compared with the traditional heuristic algorithms.

Efficient network resource utilization is crucial in Virtual Network Embedding (VNE) problem. The diversity of virtual topologies belong to various services providers (SPs) severely affects the efficiency of VNE algorithms and fairness between SPs. This paper proposes a fair VNE algorithm with a topological transformation mechanism. Such mechanism will transform virtual topology to reduce complexity. Then the algorithm will felicitously map the virtual network onto substrate network through a Disperse Particle Swarm Optimization (DPSO) based process. Simulation results show that due to the topological transformation procedure the algorithm can achieve more fairness than traditional VNE algorithms.

A novel evaluation function for higher acceptance rates and more profitable metaheuristic-based online virtual network embedding

Network virtualization (NV) has widely envisioned as a crucial factor for the success of the future networks by enabling a flexible, cost-effective and on-demand deployments of multiple network service requests on a shared physical infrastructure. The major challenge of NV is to efficiently and effectively embed heterogeneous virtual network requests (VNRs), consisting of a set of virtual nodes connected by virtual links, onto a shared substrate network meeting various stringent resource constraints. Most of the research papers in this field have merely focused on separate virtual node mapping (VNoM) or virtual link mapping (VLiM) with scalable heuristic algorithms. The lack of a coordination between node and link mapping stages results in low acceptance ratio as well as network revenues. In this paper, we propose a new approach based on Genetic Algorithm (GA) that jointly coordinates node and link mappings where the link mapping is relied on a path ranking method. A novel heuristic conciliation mechanism is introduced to handle a possible set of infeasible link mappings during gener-ating virtual embedding solutions in GA's operations. Extensive evaluation results show that our proposed GA-based algorithm outperforms state-of-the-art virtual embedding algorithms in all performance metrics we adopted.

This paper presents a platform for virtual network (VN) provisioning across multiple domains. The platform decomposes VN provisioning into multiple steps to address the implications of limited information disclosure on resource discovery and allocation. A new VN embedding algorithm with simultaneous node and link mapping allows to assign resources within each domain. For inter-domain virtual link setup, we design and realize a signaling protocol that also integrates resource reservations for providing virtual links with Quality-of-Service guarantees. Experimental results show that small VNs can be provisioned within a few seconds.

EFraS: Emulated framework to develop and analyze dynamic Virtual Network Embedding strategies over SDN infrastructure