A Meta-Heuristic based Virtual Machine Placement and Migration for Optimal Resource Utilization in the Cloud Computing Environment

Abstract

This paper focuses on the Infrastructure as a Service (IaaS) model where custom Virtual Machines (VM) are launched in appropriate hosts available in a Cloud. It is necessary to develop efficient scheduling algorithm to allocate VMs to physical resources. The proposed algorithm is based on Particle Swarm Optimization (PSO) which evaluates a cloud scheduler with an objective of optimal resource utilization in the data centers. The resource wastage model for optimal resource utilization is discussed. The proposed algorithm utilizes the cloud resources effectively by schedule or co-locates dissimilar application specific virtual machines on the host in an intelligent manner. The proposed algorithm is compared against the existing VM allocation algorithm. The results exhibit the advantages of using the proposed algorithm. VM migration is done to meet out the Service Level Agreements (SLAs) based on the proposed model. It is shown that the proposed algorithm achieved the better resource utilization and minimizes the number of VM migration.