Power Management of Cloud Datacenter in Infrastructure Level via Efficinet Virtual Machine Placement by Utilizing Hybrid Genetic Algorithm

The virtualization technology enables cloud datacenters to co-host multiple virtual machines (VMs) on a single physical machine (PM) to meet the need of different users. Efficient VM placement (VMP) schemes can significantly decrease residual power consumption in cloud infrastructure level. This paper formulates VMP to an integer linear optimization programming problem with power management perspective. To solve this NP-Hard problem, a hybrid genetic algorithm (HGA) is presented. To verify the effectiveness of proposed HGA, it was tested against other state-of-the-arts in different scenarios. The results shows that HGA beats other approaches in terms of power management and reduction of total power consumption significantly.