Citation

Xiao S, Wang S, Zhuang J, Wang T, Liu J. Sensors (Basel) 2021; 21(18): e6085.

Copyright

(Copyright © 2021, MDPI: Multidisciplinary Digital Publishing Institute)

DOI

10.3390/s21186058

PMID

unavailable

Abstract

Today, vehicles are increasingly being connected to the Internet of Things, which enables them to obtain high-quality services. However, the numerous vehicular applications and time-varying network status make it challenging for onboard terminals to achieve efficient computing. Therefore, based on a three-stage model of local-edge clouds and reinforcement learning, we propose a task offloading algorithm for the Internet of Vehicles (IoV). First, we establish communication methods between vehicles and their cost functions. In addition, according to the real-time state of vehicles, we analyze their computing requirements and the price function. Finally, we propose an experience-driven offloading strategy based on multi-agent reinforcement learning. The simulation results show that the algorithm increases the probability of success for the task and achieves a balance between the task vehicle delay, expenditure, task vehicle utility and service vehicle utility under various constraints.

Language: en

Keywords

Internet of Vehicles; mobile edge computing; reinforcement learning; Stackelberg game; task offloading