Consolidation of VMs to Improve Energy Efficiency in Cloud Computing Environments

摘要

Improvement of energy efficiency in IT is an important research topic nowadays. The reduction of operational costs, generated heat and environment impact are some of the reasons for this. Thanks to the advent of cloud computing, it is possible to improve energy efficiency in data centers by running various virtual machines in a single physical machine. However, the cloud providers generally invest in performance, not energy efficiency. This paper focuses on the problem of an energy efficient initial VM placement, and describes three new algorithms for this problem, one based on the First Fit Decreasing algorithm, and the other two based on the Best Fit Decreasing algorithm. They are compared with other algorithms in the literature, and a reduction of power consumption up to 3.24% was observed, as well a reduction of execution time in several orders of magnitude. Scripts used to analyze traces publicly provided by Google are another contribution of the paper, since they are useful for those working in mechanisms for cloud computing.