DROI: Energy-efficient virtual network embedding algorithm based on dynamic regions of interest

Abstract

Network virtualization is an important technology for the next generation of the internet. Moreover, energy-efficient virtual network embedding has gradually become a research hotspot due to the increase in energy awareness. Given the lack of consideration of substrate and virtual network topology information in energy-efficient virtual network embedding, this work applies spectral clustering based on field theory to extract substrate network features. Dynamic regions of interest are also established to find embedding areas with energy-saving potential for virtual networks. The largest matching area of a virtual network on a substrate network is identified by considering virtual network topology information. Experimental results show that the proposed approach greatly improves energy-saving relative to existing algorithms.