Mobility-based service optimization algorithm in cloud computing environment

This paper focuses on the need for mobile clients, and proposes a cloud platform architecture to deliver better services for them. The proposed cloud platform is distributed with cloud servers stratified in multiple layers. The lower-layer servers are topologically and physically closer to mobile clients, so their service quality is relatively high compared with the higher-layers. However, the higher-layer servers have lager service area, hence they can reduce server handoffs while serving for those in high mobility. Therefore, we further present two cloud server selection algorithms separately for VIP and general clients to choose the most suitable server. The algorithms take the client's mobility, server's workload and the service quality requirement of the SLA into consideration in finding the most appropriate server. Simulation experiments are also conducted to show that our algorithm could not only improve the performance of server selection but also effectively reduce server handoffs.