PENG W P, YANG Y Y, WANG G,et al.An “end-multi-edge-cloud” cooperative computation offloading algorithm based on DRL in VEC[J].Journal of Henan Polytechnic University(Natural Science) ,2024,43(6):156-163.

doi:10.16186/j.cnki.1673-9787.2022110060

Received:2022/11/28

Revised:2023/05/14

Published:2024-09-24

An “end-multi-edge-cloud” cooperative computation offloading algorithm based on DRL in VEC

PENG Weiping, YANG Yuying, WANG Ge, SONG Cheng, YAN Junhao

School of Computer Science and Technology，Henan Polytechnic University，Jiaozuo 454000，Henan，China

Abstract: Objectives To address the problems of low service quality of users and insufficient resources of edge node in vehicular edge computing（VEC），  Methods  combined vehicular edge computing with parking edge computing technology，an "end-multi-edge-cloud" cooperative computation offloading model was proposed，and a cooperative computation offloading and resource allocation algorithm based on DRL（DRL-CCORA） was designed.Firstly，the computing power of roadside parking vehicles were constructed into parking edge server（PES），which jointly provided computing services for vehicle tasks with edge node，and reduced the load of edge node.Secondly，the problem of computation offloading and resource allocation was transformed into a Markov Decision Process model，and a reward function was constructed based on time delay，energy consumption and service quality.And the computing tasks were pre-classified according to the computing resources required by the task and the maximum allowable delay of the task and the distance from the vehicle to PES，the scale of the problem was reduced.Finally，the double deep Q network（DDQN） algorithm was used to obtain the optimal strategy of computation offloading and resource allocation.  Results The results showed that，compared to the contrasting algorithm，the proposed algorithm improved the overall user service quality by more than 6.25%，improved the task completion rate by more than 10.26%，and reduced the time delay and energy consumption of task computing by more than 18.8% and 5.26%，respectively.  Conclusions The proposed algorithm optimized the load of the edge node，reduced the time delay and energy consumption of task completion，and improved the service quality of users.

Key words:vehicular edge computing;parking edge computing;computation offloading;resource allocation;double deep Q network