DAG-based Task Scheduling in Mobile Edge Computing

Abstract

Mobile edge computing (MEC) provides mobile devices with rich computation resources at the edge of networks, improving computation power of devices and quality of experience of users. In this paper, we consider the task scheduling for directed acyclic graph (DAG)-based applications in MEC and target to maximize the execution reliability given energy consumption and latency constraints. To solve this problem, we propose the Maximize Reliability Offloading Algorithm (MROA). The main idea is to decompose the given constraints and adjust the decomposed constraints dynamically. Simulation results show that our proposed algorithm achieves higher reliability than other three algorithms.