Performance Comparison of Virtual Machine Selection Policies in Cloud Environment

Abstract

Many solutions have been proposed in the past to protect data center from inefficient resource usage. However, better utilization of the resources while providing desired Quality of Services (QoS) is still an open research challenge. Researchers continuously working on novel resource management strategies focuses on Virtual Machine (VM) Placement, Load Balancing, Task Scheduling and Virtual Machine Selection for designing an optimal solution. Among these, Virtual Machine Selection has emerged as a more consistent solution to combat against such resource wastage that in turn contributes to high energy consumption. In this strategy, a careful decision of choosing a virtual machine for migration is taken since, the selection decision directly influences migration time and CPU resource utilization. A wrong selection can increase energy consumption and Service Level Agreement (SLA) violations in a data center. Literature evidences number of virtual machine selection solutions implementing Heuristic, Metaheuristic or Machine Learning techniques. This paper systematically reviews and compares commonly used Heuristic approach based Virtual Machine Selection policies. Such an exhaustive comparison will surely help the research community to provide more robust and reliable Virtual Machine Selection policy. © 2020, World Academy of Research in Science and Engineering. All rights reserved.