基于行动受限深度强化学习的C-V2X分布式通信拥塞控制研究

朱晓康; 欧阳敏; 王颐南; 王桐; 高山; 肖培

doi:null

您当前的位置：

首页 >

文章列表页 >

基于行动受限深度强化学习的C-V2X分布式通信拥塞控制研究

更新时间：2026-03-03

- 基于行动受限深度强化学习的C-V2X分布式通信拥塞控制研究
- Research on Distributed Communication Congestion Control in C-V2X Based on Action-Restricted Deep Reinforcement Learning
- 物联网学报 2026年
- 作者机构：
  
  1.哈尔滨工程大学，黑龙江哈尔滨150001
  2.黑龙江省智能感知与群体智能计算创新研究中心，黑龙江哈尔滨150001
  3.哈尔滨市公安局南岗分局网络安全保卫大队，黑龙江哈尔滨150001
  4.英国萨里大学通信系统研究所，英格兰萨里郡GU2 7XH
- 作者简介：
  
  王桐，wangtong@hrbeu.edu.cn
- 基金信息：
  
  国家自然科学基金资助项目(62372131);黑龙江省重点研发计划资助项目(2023ZX01A20)
- DOI：
  中图分类号：
- 收稿：2025-12-03，
  
  修回：2026-02-16，
  
  录用：2026-02-25，
- 稿件说明：
移动端阅览
朱晓康, 欧阳敏, 王颐南, 等. 基于行动受限深度强化学习的C-V2X分布式通信拥塞控制研究[J/OL]. 物联网学报, 2026.

ZHU Xiaokang, OUYANG Min, WANG Yinan, et al. Research on Distributed Communication Congestion Control in C-V2X Based on Action-Restricted Deep Reinforcement Learning[J/OL]. Chinese Journal on Internet of Things, 2026.
朱晓康, 欧阳敏, 王颐南, 等. 基于行动受限深度强化学习的C-V2X分布式通信拥塞控制研究[J/OL]. 物联网学报, 2026. DOI：

ZHU Xiaokang, OUYANG Min, WANG Yinan, et al. Research on Distributed Communication Congestion Control in C-V2X Based on Action-Restricted Deep Reinforcement Learning[J/OL]. Chinese Journal on Internet of Things, 2026. DOI：

摘要

对车联网领域蜂窝车联网（C-V2X

Cellular Vehicle-to-Everything）分布式拥塞控制（DCC

Distributed congestion control）在动态需求下的适应性问题进行了研究，提出了基于行动限域深度Q网络（AC-DQN

Action-confined deep Q-network）的单层和双层架构的自适应DCC算法，实现动态优化车对车(V2V

Vehicle-to-Vehicle)通信参数以提高网络数据包传输率（PDR

Packet Delivery Ratio）。该算法通过在行动域中选定范围限定的子行动域，并在子行动域中确定具体行动，实现自主调整通信参数以适应不同环境，从而缓解信道拥塞。采用集中训练、分布式部署模式，且适用于高维状态动作空间的深度强化学习(DRL

Deep reinforcement learning)算法。仿真结果表明，与现有 C-V2X DCC算法相比，所提算法在PDR 和吞吐量方面表现更优。

Abstract

This study investigates the adaptability issue of distributed congestion control (DCC) for cellular vehicle-to-everything (C-V2X) in vehicular networks under dynamic demands. It proposes adaptive DCC algorithms based on action-confined deep Q-network (AC-DQN) with single-layer and dual-layer architectures

achieving dynamic optimization of vehicle-to-vehicle (V2V) communication parameters to improve the packet delivery ratio (PDR). The algorithm autonomously adjusts communication parameters to adapt to different environments by selecting a range-limited sub-action domain within the action domain and determining specific actions within the sub-action domain

thereby alleviating channel congestion. It employs a centralized training and distributed deployment mode and is suitable for deep reinforcement learning (DRL) algorithms with high-dimensional state-action spaces. Simulation results show that compared to existing C-V2X DCC algorithms

the proposed algorithm performs better in terms of PDR and throughput.

关键词

Keywords

references

LANSFORD J . LTE-V2X technology and standards [C ] // Proceedings of the 2023 IEEE Conference on Standards for Communications and Networking (CSCN) . Piscataway : IEEE Press , 2023 : 73 - 76 .

KIM S , KIM B J , PARK B B . Environment-adaptive multiple access for distributed V2X network: a reinforcement learning framework [C ] // Proceedings of the 2021 IEEE 93rd Vehicular Technology Conference (VTC2021-Spring) . Piscataway : IEEE Press , 2021 : 1 - 7 .

MANSOURI A , MARTINEZ V , HÄRRI J . A first investigation of congestion control for LTE-V2X mode 4 [C ] // Proceedings of the 2019 15th Annual Conference on Wireless On-demand Network Systems and Services (WONS) . Piscataway : IEEE Press , 2019 : 56 - 63 .

CHEN S Z , HU J L , ZHAO L , et al . Cellular Vehicle-to-Everything (C-V2X) [M ] . Singapore : Springer Nature Singapore , 2023 : 1 - 20 .

WANG J X , YING T , ZHU K L , et al . Large scale LTE-V2X test attempt via real deployment [C ] // Proceedings of the 2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC) . Piscataway : IEEE Press , 2022 : 3146 - 3151 .

YANG W , JEON B , MUN C , et al . Cellular-V2X QoS adaptive distributed congestion control: a deep Q network approach [C ] // Proceedings of the 2023 IEEE 20th Consumer Communications & Networking Conference (CCNC) . Piscataway : IEEE Press , 2023 : 967 - 968 .

YOON Y , KIM H . Balancing power and rate control for improved congestion control in cellular V2X communication environments [J ] . IEEE Access , 2020 , 8 : 105071 - 105081 .

MAKSIMOVSKI D , LOBO S , FACCHI C . Prioritization of maneuver coordination messages and the impact of decentralized congestion control [C ] // Proceedings of the 2024 IEEE 99th Vehicular Technology Conference (VTC2024-Spring) . Piscataway : IEEE Press , 2024 : 1 - 7 .

TOGHI B , SAIFUDDIN M , FALLAH Y P , et al . Analysis of distributed congestion control in cellular vehicle-to-everything networks [C ] // Proceedings of the 2019 IEEE 90th Vehicular Technology Conference (VTC2019-Fall) . Piscataway : IEEE Press , 2019 : 1 - 7 .

ROSHDI M , BHADAURIA S , HASSAN K , et al . Deep reinforcement learning based congestion control for V2X communication [C ] // Proceedings of the 2021 IEEE 32nd Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC) . Piscataway : IEEE Press , 2021 : 1 - 6 .

SHARMA S , PANJETA M . Optimization transmit rate-based decentralized congestion control scheme in vehicular ad hoc networks [J ] . Innovations in Computational and Computer Techniques: icacct - 2021 , 2022, 2555 : 030006 .

BALADOR A , BAI C M , SEDIGHI F . A comparison of decentralized congestion control algorithms for multiplatooning communications [C ] // Proceedings of the 2019 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) . Piscataway : IEEE Press , 2019 : 674 - 680 .

SABEEH S , WESOŁOWSKI K . Congestion control in autonomous resource selection of cellular-V2X [J ] . IEEE Access , 2023 , 11 : 7450 - 7460 .

ZENG L Q , SA P B , HAN Q W , et al . DRG-DCC: a driving risk gaming based distributed congestion control method for C-V2X technology [J ] . Computers , Materials & Continua, 2025 , 83 ( 2 ): 2059 - 2086 .

EGEA-LOPEZ E , PAVON-MARIÑO P , SANTA J . Optimal joint power and rate adaptation for awareness and congestion control in vehicular networks [J ] . IEEE Transactions on Intelligent Transportation Systems , 2022 , 23 ( 12 ): 25033 - 25046 .

CHHABRA R , KRISHNA C R , VERMA S . Context-aware hybrid adaptive beaconing for driver behavior dissemination in VANETs [J ] . IETE Journal of Research , 2023 , 69 ( 7 ): 4113 - 4129 .

AZNAR-POVEDA J , EGEA-LOPEZ E , GARCIA-SANCHEZ A J , et al . Time-to-collision-based awareness and congestion control for vehicular communications [J ] . IEEE Access , 2019 , 7 : 154192 - 154208 .

MAKSIMOVSKI D , FACCHI C , FESTAG A . Packet rate control for maneuver coordination in congested V2X communication environments [C ] // Proceedings of the 2024 IEEE 100th Vehicular Technology Conference (VTC2024-Fall) . Piscataway : IEEE Press , 2024 : 1 - 6 .

JEON Y , YU S , MUN C . Poster: analyzing the impact of DCC on CACC by application and MAC layer co-simulation [C ] // Proceedings of the 2025 IEEE Vehicular Networking Conference (VNC) . Piscataway : IEEE Press , 2025 : 1 - 2 .

SEPULCRE M , GUADALCAZAR Y , FORNELL M A , et al . V2X congestion control for multi-channel operation: a scalable validation in virtualized environments [C ] // Proceedings of the 2025 IEEE 101st Vehicular Technology Conference (VTC2025-Spring) . Piscataway : IEEE Press , 2025 : 1 - 5 .

CHOI J Y , JO H S , MUN C , et al . Deep reinforcement learning-based distributed congestion control in cellular V2X networks [J ] . IEEE Wireless Communications Letters , 2021 , 10 ( 11 ): 2582 - 2586 .

SEHLA K , NGUYEN T M T , PUJOLLE G , et al . Resource allocation modes in C-V2X: from LTE-V2X to 5G-V2X [J ] . IEEE Internet of Things Journal , 2022 , 9 ( 11 ): 8291 - 8314 .

ZHANG X R , PENG M G , YAN S , et al . Deep-reinforcement-learning-based mode selection and resource allocation for cellular V2X communications [J ] . IEEE Internet of Things Journal , 2020 , 7 ( 7 ): 6380 - 6391 .

CHUNG Y C , CHANG H Y , CHANG R Y , et al . Deep reinforcement learning-based resource allocation for cellular V2X communications [C ] // Proceedings of the 2023 IEEE 97th Vehicular Technology Conference (VTC2023-Spring) . Piscataway : IEEE Press , 2023 : 1 - 7 .

NGUYEN L H , NGUYEN V L , KUO J J . Efficient reinforcement learning-based transmission control for mitigating channel congestion in 5G V2X sidelink [J ] . IEEE Access , 2022 , 10 : 62268 - 62281 .

LUONG N C , HOANG D T , GONG S M , et al . Applications of deep reinforcement learning in communications and networking: a survey [J ] . IEEE Communications Surveys & Tutorials , 2019 , 21 ( 4 ): 3133 - 3174 .

SAAD M M , TARIQ M A , SEO J , et al . Age-of-information aware intelligent MAC for congestion control in NR-V2X [C ] // Proceedings of the 2023 Fourteenth International Conference on Ubiquitous and Future Networks (ICUFN) . Piscataway : IEEE Press , 2023 : 265 - 270 .

TIAN J W , AN S , ISLAM A , et al . A hybrid power-rate management strategy in distributed congestion control for 5G-NR-V2X sidelink communications [J ] . Sensors , 2023 , 23 ( 15 ): 6657 .

3GPP TS 38.214 V16.14.0 NR; Physical layer procedures for data (Release 16) [S ] .

ZHOU X K , HUI F , LIU J J , et al . Resource reservation in C-V2X networks for dynamic traffic environments: from vehicle density-driven to deep reinforcement learning [J ] . IEEE Transactions on Vehicular Technology , 2025 , 74 ( 11 ): 17429 - 17444 .

3GPP TS 36.101 V14.8.0 Technical specification group radio access network; Evolved universal terrestrial radio access (E-UTRA); User equipment (UE) radio transmission and reception [S ] .

MNIH V , KAVUKCUOGLU K , SILVER D , et al . Human-level control through deep reinforcement learning [J ] . Nature , 2015 , 518 ( 7540 ): 529 - 533 .

FOERSTER J N . Deep multi-agent reinforcement learning [D ] . Oxford : University of Oxford , 2018 .

3GPP TS 38.101-1 NR; User equipment (UE) radio transmission and reception; Part 1: Range 1 standalone [S ] .

CECCHINI G , BAZZI A , MASINI B M , et al . LTEV2Vsim: an LTE-V2V simulator for the investigation of resource allocation for cooperative awareness [C ] // Proceedings of the 2017 5th IEEE International Conference on Models and Technologies for Intelligent Transportation Systems (MT-ITS) . Piscataway : IEEE Press , 2017 : 80 - 85 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

车联网中联邦学习模型低时延传输迁移方法研究

基于Decision Transformer模型的5G基站节能控制策略优化新范式研究

基于强化学习的能量采集传感器传输功率控制方法

无人机集群协同主动搜索的强化学习策略研究