Research Article
Comprehensive Task Priority Queue for Resource Allocation in Vehicle Edge Computing Network Based on Deep Reinforcement Learning
@INPROCEEDINGS{10.1007/978-3-031-31275-5_13, author={Zhaonian Li and Changxiang Chen and ZhenJiang Zhang}, title={Comprehensive Task Priority Queue for Resource Allocation in Vehicle Edge Computing Network Based on Deep Reinforcement Learning}, proceedings={Smart Grid and Internet of Things. 6th EAI International Conference, SGIoT 2022, TaiChung, Taiwan, November 19-20, 2022, Proceedings}, proceedings_a={SGIOT}, year={2023}, month={5}, keywords={vehicle edge computing network SDN comprehensive task priority queue task offloading DDPG}, doi={10.1007/978-3-031-31275-5_13} }- Zhaonian Li
Changxiang Chen
ZhenJiang Zhang
Year: 2023
Comprehensive Task Priority Queue for Resource Allocation in Vehicle Edge Computing Network Based on Deep Reinforcement Learning
SGIOT
Springer
DOI: 10.1007/978-3-031-31275-5_13
Abstract
The rapid increase in the number of vehicles and their intelligence have led to the lack of calculation resource of original network. However, the framework like vehicle-to-roadside infrastructure is still faced with the challenge of balancing the impact of time and energy consumption. To overcome these drawbacks, this paper establishes a comprehensive task priority queue on the basis of software defined network (SDN) based vehicular network instead of randomly offloading the tasks. According to the task type and vehicle speed, different tasks are graded and a joint optimization problem for minimizing the vehicles’ time and energy consumption is formulated. Deep deterministic policy gradient (DDPG) algorithm is proposed to simulate the optimal resource allocation strategy of VEC model in the paper. Finally, this paper analyze the significance of the proposed model by giving numerical results.
