Offloading Dependent Tasks with Mobility in Mobile Edge Computing

Abstract

With the rise in computation-intensive and delay-sensitive applications, the limited resource of the user device has become a significant challenge. Mobile Edge Computing(MEC) has emerged as a paradigm to compensate for the resource shortage. When offloading application’s tasks to the Mobile Edge Network(MEN) of the MEC with consideration of task dependency and resource usage, the offloading process also requires consideration of user device’s mobility. However, most existing research that consider user mobility or task dependency among several factors assume that the offloaded tasks in the MEC are parallelizable or that the user device is immobile. Nev-ertheless, real-world applications have sequential dependencies and user devices are frequently mobile. In this situation, the previous methods no longer apply. In this paper, we propose a novel algorithm that jointly considers task dependency and user mobility to minimize application completion time in MEN. We show the improved performance of our proposed algorithm over the existing research.