Coordinated Power and Performance-Efficient Virtual Machines Scheduling in the Cloud

Abstract

Cloud computing with live migration technique is considered as one of the most promising ways to cope with power consumption and performance management of a data center. Most prior works on performance and power management of the whole server farm are achieved in a separate way. To address this issue, in this paper we propose an efficient method for the whole server farm, which aims to dynamically consolidate virtual machines in a coordinated way that optimizes the energy and performance trade-off. Firstly, we focus on the virtual machine (VM) selection step. Then we consider the VM selection task as a Dynamic Decision-Making (DDM) problem and construct a coordinated cost function with power and performance. In this study, the Q-Learning strategy of Reinforcement Learning (RL) is adopted to solve this DDM problem. The proposed algorithm is simulated in CloudSim toolkit using real-world workload traces. Finally, experimental results indicate that our approach outperforms other algorithms in terms of energy consumption, the number of VM migrations, average SLA violation and the number of host shutdowns.