Scaling Down Power Utilization with Optimal Virtual Machine Placement Scheme for Cloud Data Center Resources: A Performance Evaluation

Abstract

Cloud computing provides IT Services to the user throughout the world according to their needs. There is a huge usage of electric power dues to the accelerating demand for large scale data centres required for processing potential, by scientific web operations. To provide high-level computation in large scale for a distributed system such as clouds an enormous amount of energy is consumed and handling this energy by applying an optimal virtual machine scheme is a major task. We have defined an architectural framework for energy conscious mapping of available virtual machines to appropriate data center resources in addition to dynamic combination of virtual machine scheduling scheme in this paper. Clusters of the server are contained by the cloud infrastructure modelled. It also represents the cluster management and the factors inside the clusters. Also, the data recovery is presented in a best possible way, taking in consideration that backup not only act as a backup but also helpful in the energy consideration process, by using two space backup (one in guiding cluster and one at secondary cluster) making model more powerful and resistible in case of data recovery. Experiments results demonstrate that the performance of the proposed scheme is found to be remarkable in comparison to the other state-of-the-art competing scheme of its class.