Multi-Objective Virtual Machine Placement Algorithm Based on Particle Swarm Optimization

Abstract

According to the cloud computing paradigm, cloud services make use of Virtual Machines (VMs) that are running on Physical Machines (PMs). A user consumes VMs that are hosted on PMs located at one or several data centers. Energy consumption of a data center is highly correlated with the number of active PMs. A data center relies on a placement algorithm to assign the required VMs on a minimum number of PMs in order to minimize energy consumption. In this paper, we propose a VM placement algorithm based on Particle Swarm optimization (PSO) meta-heuristics. As opposed to reported VM placements, which all seek to minimize either energy consumption or resource wastage, our proposed PSO algorithm seeks to maximize packing efficiency while minimizing energy consumption. Extensive simulation results show that our algorithm significantly produces better results when compared to suggested work. Indeed, the solutions obtained with our algorithm require a lower number of PMs, lower energy consumption and a better balanced utilization of PMs.