Topology-aware virtual network embedding through the degree

Abstract

As a promising technology, Network Virtualization plays a vital role in Cloud Computing and Data Center Networks by allowing multiple heterogeneous virtual networks to run simultaneously on a shared substrate network. A fundamental challenge in Network Virtualization is the Virtual Network Embedding (VNE) problem: how to effectively embed various virtual networks onto shared physical nodes and links in the substrate network. Previous research presents many heuristic algorithms, but barely considers topological attributes of substrate and virtual networks, which may lead to decreased utilization of substrate resources. In this paper, we advocate utilizing topological attributes of substrate and virtual networks in the VNE problem, and propose a topology-aware VNE algorithm based on the degrees of nodes. Due to overall consideration of substrate and virtual networks, our study better coordinates node and link embedding. Extensive simulations demonstrate that our proposed algorithm significantly improves the long-term average revenue, acceptance ratio, and revenue/cost ratio compared to previous algorithms.