An Effective Virtual Machine Selection Approach for Dynamic Consolidation in Cloud Computing Environment

Exponential increasing Cloud Computing services has resulted in setting up large scale virtual Cloud Computing data centres throughout the globe. The increased use in cloud data centres resulted in a tremendous increase in power consumption, and carbon footprint. Therefore, it is an urgent requirement for developing effective methods to reduce their power consumption while meeting service level agreements between cloud service providers and users. Virtual machine consolidation is an effective method for reducing power consumption of data center. Selecting a suitable virtual machine for migrating from over utilized physical machines to others during the virtual machine consolidation process is challenging. This work proposes a power saving virtual machine selection method based upon the current utilization and resource capacity of virtual and physical machines to reduce their power consumption. The proposed approach is validated experimentally in a simulated environment using cloudSim. Its performance is analyzed by measuring power consumption, virtual machine migrations, service level agreement violations, and a combined metric of energy consumption and service level agreement violations. Comparative analysis of the result demonstrates the superiority of the proposed approach. The proposed approach has resulted in significant improvement in the power reduction of cloud data centers.