DOI number:10.1504/IJSNET.2023.130711
Journal:INTERNATIONAL JOURNAL OF SENSOR NETWORKS
Key Words:task oloading; vehicular edge computing; dependent task; deep reinforcement learning
Abstract:Various interdependent and computationally intensive on-vehicle tasks have posed great pressure on the computing power of vehicles. Vehicular edge computing (VEC) is considered to be a promising paradigm to solve this problem. However, due to the high mobility, vehicles will pass through multiple road-side units (RSUs) during task computing. How to coordinate the oloading decision of RSUs is a challenge. In this study, we ropose a dependent task oloading scheme by considering vehicle mobility, service availability, and task priority. Meanwhile, to coordinate the oloading decisions among the RSUs, a Markov decision process (MDP) is carefully designed, in which the action of each RSU is divided into three steps to decide whether, where, and how each task is oloaded separately. Then, an advanced DDPG-based deep reinforcement learning (DRL) algorithm is adopted to solve this problem. Simulation results show that the proposed scheme has better performance in reducing task processing latency and consumption.
Co-author:Jianing Shi,Benhong Zhang,Zengwei Lyu,Lingjie Huang
First Author:Xiang Bi
Indexed by:Journal paper
Discipline:Engineering
Document Type:J
Volume:41
Issue:4
Page Number:244-256
ISSN No.:1748-1279
Translation or Not:no
Date of Publication:2023-05-01
Included Journals:SCI