Q-Learning Based Joint PC-5/Uu Offloading Strategy for C-V2X Based Vehicular Edge Computing System

被引：0
|
作者：
Feng W.-Y. [1 ]
Lin S.-Y. [1 ,2 ]
Feng J.-T. [1 ]
Li Y. [3 ]
Kong F.-P. [4 ]
Ai B. [1 ,5 ]
机构：
[1] School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing
[2] Collaborative Innovation Center of Railway Traffic Safety, Beijing
[3] Information Dispatch Center, China Railway Information Technology Group Co.，Ltd., Beijing
[4] Information Technology Laboratory, China Railway Information Engineering Group Network Technology Research Institute Co.，Ltd., Beijing
[5] Frontiers Science Center for Smart High-Speed Railway System, Beijing
来源：
Tien Tzu Hsueh Pao/Acta Electronica Sinica | 2024年 / 52卷 / 02期
基金：
中国国家自然科学基金;
关键词：
cellular vehicular-to-everything; computation offloading; constrained Markov decision process; edge computing; Q learning;
D O I：
10.12263/DZXB.20220922
中图分类号：
学科分类号：
摘要：
Intelligent transportation services, such as smart driving, put forward high requirements for latency. When the vehicle itself has insufficient computing power, the vehicle needs the surrounding vehicles and roadside edge computing units to help it complete the task computation. In this paper, based on the existing vehicular edge computing (VEC) offloading strategy, considering the differences between the 5G-NR interface and PC-5 interface link of cellular-V2X (C-V2X) system, we propose a Q-Learning based joint PC-5/Uu interface edge computing offloading strategy. The successful transmission probability of PC-5 link in C-V2X system is modeled, and then the transmission rate characterization method of PC-5 link is deduced. We formulate a constrained Markov decision process (CMDP) to minimize the system latency, where the objective function is the task processing latency in C-V2X system, and constraints are transmission power at task vehicle and energy consumption of computation at vehicles with edge computing unit. By Lagrangian approach, the CMDP problem is transformed into an equivalent min-max non-constrained MDP problem, and Q-Learning is introduced to design the offloading strategy, and then the offloading strategy of C-V2X based VEC system based on Q-Learning is proposed. Simulation results show that compared with other baseline schemes, the proposed algorithm can significantly improve the system latency performance by at least 27.3%. © 2024 Chinese Institute of Electronics. All rights reserved.
引用
收藏
页码：385 / 395
页数：10
相关论文
共 34 条
  • [1] ZHANG N, ZHANG S, YANG P, Et al., Software defined space-air-ground integrated vehicular networks: Challenges and solutions, IEEE Communications Magazine, 55, 7, pp. 101-109, (2017)
  • [2] CUI Y Y, ZHANG D G, ZHANG T, Et al., A multi-user fine-grained task offloading scheduling approach of mobile edge computing, Acta Electronica Sinica, 49, 11, pp. 2202-2207, (2021)
  • [3] YUE G X, DAI Y S, YANG X H, Et al., Model of cloud-edge cooperative service for maritime edge computing, Acta Electronica Sinica, 49, 12, pp. 2407-2418, (2021)
  • [4] ZHANG Y X, DUAN S J, ZHANG D Y, Et al., Transparent computing: Development and current status, Chinese Journal of Electronics, 29, 5, pp. 793-811, (2020)
  • [5] HUANG C, LU R X, CHOO K K R., Vehicular fog computing: Architecture, use case, and security and forensic challenges[J], IEEE Communications Magazine, 55, 11, pp. 105-111, (2017)
  • [6] LIAO Y, TIAN X Y, CAI Z R, Et al., Intelligent channel estimation based on edge computing for C-V2I, Acta Electronica Sinica, 49, 5, pp. 833-842, (2021)
  • [7] FENG W Y, YANG S Z, GAO Y, Et al., Reverse offloading for latency minimization in vehicular edge computing, ICC 2021 - IEEE International Conference on Communications, pp. 1-6, (2021)
  • [8] FENG W Y, LIN S Y, ZHANG N, Et al., Joint C-V2X based offloading and resource allocation in multi-tier vehicular edge computing system, IEEE Journal on Selected Areas in Communications, 41, 2, pp. 432-445, (2023)
  • [9] AHSAN KAZMI S M, OTOUM S, HUSSAIN R, Et al., A novel deep reinforcement learning-based approach for task-offloading in vehicular networks, 2021 IEEE Global Communications Conference (GLOBECOM), pp. 1-6, (2021)
  • [10] FENG W Y, ZHANG N, LI S C, Et al., Latency minimization of reverse offloading in vehicular edge computing[J], IEEE Transactions on Vehicular Technology, 71, 5, pp. 5343-5357, (2022)
1234