Distributed Task Offloading in Mobile-Edge Computing With Virtual Machines

Abstract

Mobile edge computing (MEC) offloads computation intensive tasks of individual users to computing clouds to alleviate the computing loads. Virtual machines (VMs), in practice, are often adopted to realize the parallel computing feature of MEC clouds. A careful local interaction among VMs further reduces the overall computing latency. However, their management turns out quite challenging in practical wireless MEC networks. This paper aims at minimizing the latency of the overall MEC task with the min-max criterion. To this end, a novel distributed strategy is developed for the joint management of the task allocation and the offloading balance among VMs. This task offloading protocol is carried out through a message-passing framework that enables a simultaneous consideration of the min-max criterion about multiple MEC tasks. The numerical results demonstrate that the proposed scheduling for distributed MEC operations achieves a 40% improvement in network utility performance over existing optimization techniques.