Quality of Experience Aware Task Offloading in Digital Twinning Vehicular Edge Computing

Adopting Digital Twin (DT) technology in vehicular edge computing (VEC) enables efficient capture of real-time state information of applications, thereby addressing complex task scheduling problems. Existing literature studies considered only minimizing service latency for task offloading; however, there is room for exploring strategies to enhance user Quality of Experience (QoE) in timeliness and reliability domains. In this paper, we have developed an optimization framework using Mixed Integer Linear Programming (MILP), namely QuETOD, which minimizes service latency by allocating task execution responsibility to highly reliable and reputed vehicles in a DT-enabled VEC environment. The developed QuETOD framework clusters the vehicles based on the demand-supply theory of economics by considering computing resources and utilizing the multi-weighted subjective logic for getting the proper reputation update of the vehicles. The experimental results of the developed QuETOD system depict significant performance improvement in terms of QoE and reliability compared to the state-of-the-art works as high as 15% and 25%, respectively.

I. INTRODUCTION

The Internet of Vehicles (IoV) is an indispensable component of the intelligent transportation system. This technology helps to enable autonomous driving, real-time traffic behavior analysis, obstacle detection, and sensor data analysis, which requires extensive processing of the massive amount of data in real-time [1]. However, high mobility and resource competition among the vehicles, time-varying vehicular network topology, and channel quality pose significant challenges for energy-efficient, reliable, and timely execution of tasks in the vehicular edge computing (VEC) environment [2].