Energy-Efficient and Load-Aware VM Placement in Cloud Data Centers

Abstract VM consolidation has been proposed as an effective solution to improve resource utilization and energy efficiency through migration. Improper placement during may cause frequent migrations constant on–off switching of PMs, which can significantly hurt QoS increase consumption. Most existing algorithms on efficient suffer the problem easily falling into a sub-optimum prematurely since they are heuristic. Also, do not achieve good balance between multiple different goals, such utilization, QoS, efficiency. To address this problem, we propose approach called MOEA/D-based placement, with goal optimizing utilization. We develop improved MOEA/D algorithm search for Pareto-compromise placement. Our experiment results demonstrate that multi-objective optimization (MOO) model have immense potential it offers significant cost savings improvement in under dynamic workload scenarios.