An energy-efficient approach for virtual machine placement in cloud based data centers

Abstract

Cloud computing is a new technology which is proffering IT services based on pay-as-you-go model to consumers from everywhere in the world. The growing demand of Cloud infrastructure and modern computational requests like business, scientific and web applications result in large-scale data centers and lead to extra electrical energy consumption. High energy consumption causes high operational cost and also led to high carbon emission which is harmful for atmosphere. Hence, energy-efficient techniques are required to minimize the negative effects of Cloud computing on the environment. Virtual machines (VMs) migration, dynamic consolidation in the virtualized data centers in cloud environments and switching idle physical machines off could yield reduce energy consumption; hence, one of the important issues for energy efficiency in virtualized cloud environments is how to place new VMs or selected VMs for migration across the hosts. In this paper we propose an energy-efficient approach based on Minimum Correlation Coefficient (MCC) method for virtual machine placement in cloud based, virtualized data centers. The proposed approach regards both Service Level Agreement (SLA) and low energy consumption and tries to make a trade-off between these two concerns using fuzzy Analytic Hierarchy Process (AHP). We evaluate our approach using Cloudsim toolkit as a modern cloud computing environment simulator. The evaluation shows that our proposed method offers a suitable trade-off between power efficiency and SLA violation reduction in cloud data centers.