An ACO-based Scheduling Strategy on Load Balancing in Cloud Computing Environment

Abstract

Overload balance of cloud data centers is a matter of great concern. Live migration of virtual machines presents an effective method to realize load balancing and to optimize resources utilization. With the rapidly increasing scale of cloud data centers, traditional centralized migration strategy begins to show lack of scalability and reliability. In this paper, we propose a novel distributed VM migration strategy based on a metaheuristic algorithm called Ant Colony Optimization. In our ACO-VMM Strategy, local migration agent autonomously monitors the resource utilization and launches the migration. At monitoring stage, it takes both the previous and current system condition into account to avoid unnecessary migrations. Besides, it adopts two different traversing strategies for ants in order to find the near-optimal mapping relationship between virtual machines (VMs) and physical machines (PMs). Experimental results show that ACO-VMM outperforms the existing migration strategies by achieving load balance of whole system, as well as reducing the number of migrations and maintaining the required performance levels.