Live Migration Overhead-Aware Dynamic VM Consolidation Algorithm in Cloud Computing

Abstract

Energy Efficiency has become a crucial concern in modern data centers. Dynamic VM consolidation is one of the effective approaches endorsed to achieve energy efficiency in cloud data centers hosting thousands of servers. Live migration is a core feature enabling VM consolidation. However, live migration is a costly operation imposing energy and performance overhead. An efficient dynamic virtual machine consolidate should consider the cost due to live migration. In this paper, we design and implement a dynamic VM consolidation algorithm based on simulated annealing that accounts for the migration cost imposed by a consolidation plan. We conduct simulation-based experiments on CloudSim using real cloud workload traces from PlanetLab to evaluate the performance of the proposed algorithm. Results show that the using the proposed algorithm, the simulated data center consumes almost the same amount of energy of that using a FF based consolidation. However, the proposed algorithm accounts for the cost due to live migration and hence, reducing SLA violations and performance degradations.