Comparison of different data center location policies in survivable elastic optical networks

Abstract

In this paper, we focus on the important problem of locating data centers (DCs) in elastic optical network (EON). We propose to use both topology-based (that follow directly from the network graph structure) and demographic-economical (characteristics of the cities that correspond to network nodes) data to define DC location policies. In particular, we define 7 different DC location polices, which can be classified as topology-based, demographic-economical, and hybrid (use both groups of information). The policies are applied to determine location of DCs for two realistic network topologies. Next, we solve routing and spectrum allocation (RSA) problem in EON protected by a dedicated path protection (DPP) with realistic traffic demands generated with respect to demographic-economical model. The obtained results are analyzed in order to compare different DC location policies according to the spectrum usage and possibility to improve network survivability in case of a random large-scale disaster. The results of our investigation prove, that DC location policy has a crucial influence on the network performance (in terms of the spectrum usage and survivability provisioning), especially when the number of available DCs is relatively small. What is more, according to the results topology-based DC location policies significantly outperform demographic-economical methods in terms of both performance metrics.