Migration Decision for Hybrid Mobility in Reconfigurable Virtual Machines

Virtual machine (VM) is an important mechanism to multiplex computer resource. The increasing popularity of Grid computing and Peer-to-Peer systems has renewed research interests in dynamic and adaptive virtual machines. Service migration is a vital technique to construct reconfigurable VMs. By incorporating mobile agent technology, VM systems can improve their resource utilization, load balancing and fault tolerance significantly via hybrid mobility of services and computational agents. This paper focuses on the decision problem of hybrid mobility for load-balancing in reconfigurable VMs. We tackle this problem from three aspects: migration candidate determination, migration timing and destination server selection. The service migration timing and destination server selection are formulated as two optimization models. We derive the optimal migration policy for heterogenous distributed systems based on stochastic optimization theories. Renewal processes are applied to model the dynamics of migration. We model the agent migration problem by dynamic programming and extend the optimal service migration timing by considering dynamic composition of agents. Our decision policy is complementary to the existing service and agent migration techniques. Its accuracy is verified by simulations.