Comparison of D-Vine and R-Vine Techniques for Virtual Network Embedding Problem

Abstract

In Network virtualization, Virtual Network Embedding(VNE) is the process of mapping virtual nodes and links of a virtual network request(VNR) on a substrate network to fulfill the demands of the request. Embedding virtual network requests helps in achieving network virtualization efficiently. This paper presents Vineyard, a set of VN embedding algorithms namely D-Vine and R-Vine, to introduce a finer correlation between the node mapping and link mapping phases. Deterministic Virtual Network Embedding(D-Vine) algorithm is used to embed virtual nodes on to substrate network based on the capacity constraint when it is not satisfied the system takes the Randomised Virtual Network Embedding(R-Vine) algorithm to map the nodes based on location constraint. Subsequently, after the nodes are embedded the link mapping phase is done based on the distance constraint. A window-based virtual embedding algorithm(W-Vine) is also introduced to evaluate the effect of lookahead in Virtual Network Embedding. After the mapping of multiple virtual network requests, analysis is done to compare the node and CPU utilization in both the algorithms and the variations are conserved.