Mobiles on cloud nine: Efficient task migration policies for cloud computing systems

Due to limited processing and energy resources, mobile devices outsource their computationally intensive tasks to the cloud. However, clouds are shared facilities and hence task execution time may vary significantly. In this paper, we investigate the potential of task migrations to reduce contention for the shared resources of a mobile cloud computing architecture in which local clouds are attached to wireless access infrastructure (e.g. wireless base stations or access points). We devise online migration strategies that at each time make migration decisions according to the instantaneous load and the anticipated execution time. We explicitly take into account the interaction of co-located tasks in a server and the cost of migrations. We propose three classes of migration policies, ranging from fully uncoordinated ones, in which each user or server autonomously makes its migration decisions, up to cloud-wide ones, where migration decisions are made by the cloud provider. The key underlying idea is that a migration should occur only if it is beneficial for the processing time of the task, including the migration delay.