Joint Optimization for Bandwidth Utilization and Delay Based on Particle Swarm Optimization

Abstract

One of the most significant problems in large-scale applications is how to allocate requests from end-users to datacenters. Most existing studies focus only on high bandwidth utilization of datacenters or low request delay of end-users, lacking the consideration of both at the same time. To achieve the joint optimization for bandwidth utilization of datacenter providers and delay of end-users, this paper proposes a novel Particle Swarm Optimization (PSO) based request allocation algorithm, based on the construction of a mathematical model for joint optimization. The algorithm adapts the coding scheme and redefines the operator to make PSO suitable for discrete optimization problems and use fitness function to get a global optimal solution. Through extensive simulations, it is demonstrated that the PSO based request allocation algorithm proposed in this study can improve the bandwidth utilization and keep the average request delay within acceptable limits or even better.