A QoE-based Optimization Approach to Computation Offloading in Vehicle-assisted Multi-access Edge Computing

In recent years, multi-access edge computing (MEC) has been proposed to provide low-latency computing services for mobile devices (MDs) by enabling computation task offloading from MDs to nearby MEC servers. However, the computing resources of a MEC server is usually limited and unable to satisfy the ever-increasing demand of task requests. To tackle this challenge, in this paper, we investigate a vehicle-assisted MEC (vMEC) paradigm, which expands the current available resources of a MEC server by integrating it with the resources of vehicular nodes (VNs) for task offloading from MDs. We propose a new utility optimization approach that factors in quality of experience (QoE) metrics to address the problem of computation offloading in vMEC. Simulation results validate the advantage of our proposal.

I. Introduction

In accordance with the proliferation of smart mobile devices (MDs), many new services are emerging such as virtual reality, augmented reality, face recognition, cloud gaming, etc. These services requires low latency and computing power that can not be met by MDs with inherent resource poverty. Moreover, they cannot tolerate the unpredictable high network latency of cloud computing, too.