An Energy-Efficient Consolidation of Virtual Machines in Cloud Data Centers

Abstract

The problem of migrating virtual machines (VMs) among different physical hosts is vital for resource utilization and carbon dioxide (CO2) minimization in cloud data centers. The main objective of this paper is to introduce the proposed technique CPU Utilization Variance (CUV). CUV is based on selecting the best VMsfrom overutilized servers and migrating them into other servers to save the utilized resources and not to violate the Service Level Agreements established between the end users and cloud service provider.CUV alsochooses the most appropriate host to allocate these VMs by calculating the minimum variance of all CPU utilization between all physical servers. CUVis implemented in a large-scale data center composed of 800 physical hosts and the results obtained by CloudSim tool are in terms of energy consumption in KWh, performance in Million Instructions per Second (MIPS), number of VM migrations and Service Level Agreement Violation. Further, a comparative study has been performed between CUV and recently researches for evaluating it, which achieved high performance and lower energy consumption without violating the service level agreements in a large-scale data centers