Performance-aware Energy-efficient Virtual Machine Placement in Cloud Data Center

This paper studies how to consolidate Virtual Machines (VMs) on physical severs in order to minimize the energy consumption in Cloud data centers. In Cloud data centers, a major energy consumption component is the physical servers, and it is a way to save the energy by consolidating VMs onto fewer VMs and shut down the idle physical servers. However, executing more VMs on fewer physical servers should degrade the VM performance. Accordingly, how to consolidate VMs but guarantee the VM performance is an important issue to study. To this end, we first formulate the VM consolidation problem as a mathematic model and then prove that it is equivalent to a generalized constrained minimum k-cut problem, which is the hardest NP-hard problem. Due to the problem complexity, an efficient heuristic named PEVMP (Performance-aware Energy-efficient Virtual Machine Placement) is proposed to solve it. In addition, we extend the PEVMP to be an online version to handle service dynamics. Extensive simulation results show that PEVMP can save up to 36.78% energy, and the performance of online algorithm is close to the offline result.