Mobility-Aware Multi-User Offloading Optimization for Mobile Edge Computing

Mobile Edge Computing (MEC) is a new computing paradigm with great potential to enhance the performance of user equipment (UE) by offloading resource-hungry computation tasks to lightweight and ubiquitously deployed MEC servers. In this paper, we investigate the problem of offloading decision and resource allocation among multiple users served by one base station to achieve the optimal system-wide user utility, which is defined as a trade-off between task latency and energy consumption. Mobility in the process of task offloading is considered in the optimization. We prove that the problem is NP-hard and propose a heuristic mobility-aware offloading algorithm (HMAOA) to obtain the approximate optimal offloading scheme. The original global optimization problem is converted into multiple local optimization problems. Each local optimization problem is then decomposed into two subproblems: a convex computation allocation subproblem and a non-linear integer programming (NLIP) offloading decision subproblem. The convex subproblem is solved with a numerical method to obtain the optimal computation allocation among multiple offloading users, and a partial order based heuristic approach is designed for the NLIP subproblem to determine the approximate optimal offloading decision. The proposed HMAOA is with polynomial complexity. Extensive simulation experiments and comprehensive comparison with six baseline algorithms demonstrate its excellent performance.

I. Introduction

With the rapid development of Internet of things, user equipment (UE), e.g., mobile phone, wearable device, and vehicle terminal, becomes prevalent and smarter, which boosts the proliferation of novel mobile applications, such as augmented reality, natural language processing, and face recognition. Most of these applications are computation-intensive, latency-sensitive, and bandwidth-demanding. However, the resources in UEs are usually limited. It is difficult to support these emerging applications with merely onboard systems. Mobile cloud computing (MCC) was proposed to solve this problem [1]. By offloading resource-intensive tasks to the powerful remote cloud, MCC brings several benefits: prolonging battery life, supporting sophisticated computations, and providing potentially unlimited storage.