Self regulatory graph based model for managing VM migration in cloud data centers

Cloud Computing involves the concepts of parallel processing and distributed computing in order to provide the shared resources by means of Virtual Machines(VMs) hosted by physical servers. Efficient management of VMs directly influences resource utilization and QoS delivered by the system. As the cloud setting is dynamic in nature, the number of VMs distributed among the physical servers tends to become uneven over a period of time. Under this circumstance, VMs must be migrated from overloaded server to underloaded server to balance the load. In this paper, we present a random graph model of the network of servers in a data center. By initiating random walks and using the heuristics Maximum Correlation Coefficient and Migration Opportunity, we select the migrating set of VMs as well as the target server respectively. Simulation results show that the model always finds a target server in minimum time. Also the graph maintains uniform average degree which shows that the network of physical servers remains load balanced even when the load and the migration opportunity vary with time.