A Multi-objective Virtual Machine Migration Policy in Cloud Systems

Abstract

In a Cloud computing environment, the workload fluctuates dynamically producing undesirable situations such as load imbalance, lower utilization or workload hotspots. In such cases, virtual machine migration is a potential solution. However, an algorithm based on a single objective (e.g. service-level agreement) is usually used to direct the migration process. On the contrary, there exist unconsidered conflicting factors impacting the migration process such as load volume, power consumption and resource wastage. In this paper, we consider the migration process as a multi-objective problem where the objectives are typically non-commensurable. Therefore, we propose a novel migration policy consolidated by a new elastic multi-objective optimization strategy to evaluate different objectives (including migration cost) simultaneously, and to provide the flexibility for manipulating different cases. We have tested the proposed policy through an extensive set of simulation experiments using CloudSim, and the results ensure the efficiency of our policy to control the system performance by adjusting the migration objectives to suit various workload situations.