Migrate or not? exploiting dynamic task migration in mobile cloud computing systems

Abstract

Contemporary mobile devices generate heavy loads of computationally intensive tasks, which cannot be executed locally due to the limited processing and energy capabilities of each device. Cloud facilities enable mobile devices-clients to offload their tasks to remote cloud servers, giving birth to Mobile Cloud Computing (MCC). The challenge for the cloud is to minimize the task execution and data transfer time to the user, whose location changes due to mobility. However, providing quality of service guarantees is particularly challenging in the dynamic MCC environment, due to the time-varying bandwidth of the access links, the ever changing available processing capacity at each server and the timevarying data volume of each virtual machine. In this article, we advocate the need for novel cloud architectures and migration mechanisms that effectively bring the computing power of the cloud closer to the mobile user. We consider a cloud computing architecture that consists of a back-end cloud and a local cloud, which is attached to wireless access infrastructure (e.g. LTE base stations). We outline different classes of task migration policies, spanning fully uncoordinated ones, in which each user or server autonomously makes its migration decisions, up to the cloud-wide migration strategy of a cloud provider. We conclude with a discussion of open research problems in the area.