Energy-Aware Virtual Network Embedding Approach for Distributed Cloud

TL;DR

This paper introduces an energy-efficient virtual network embedding method for distributed clouds using a particle swarm optimization approach combined with Heavy Clique Matching, improving resource allocation and energy consumption.

Contribution

It presents a novel energy-aware VNE algorithm that partitions virtual networks into subgraphs and optimizes embedding in distributed cloud environments.

Findings

Outperforms existing algorithms in simulations

Reduces energy consumption in virtual network embedding

Enhances resource utilization efficiency

Abstract

Network virtualization has caught the attention of many researchers in recent years. It facilitates the process of creating several virtual networks over a single physical network. Despite this advantage, however, network virtualization suffers from the problem of mapping virtual links and nodes to physical network in most efficient way. This problem is called virtual network embedding ("VNE"). Many researches have been proposed in an attempt to solve this problem, which have many optimization aspects, such as improving embedding strategies in a way that preserves energy, reducing embedding cost and increasing embedding revenue. Moreover, some researchers have extended their algorithms to be more compatible with the distributed clouds instead of a single infrastructure provider ("ISP"). This paper proposes energy aware particle swarm optimization algorithm for distributed clouds. This algorithm aims to partition each virtual network request ("VNR") to subgraphs, using the Heavy Clique Matching technique ("HCM") to generate a coarsened graph. Each coarsened node in the coarsened graph is assigned to a suitable data center ("DC"). Inside each DC, a modified particle swarm optimization algorithm is initiated to find the near optimal solution for the VNE problem. The proposed algorithm was tested and evaluated against existing algorithms using extensive simulations, which shows that the proposed algorithm outperforms other algorithms.