|
|
|
| Resource allocation method in vehicular networks based on hypergraph neural networks |
Peifeng LIU1( ),Fan YANG1,Jie HUANG1,Chengbo YU1,2,*() |
1. School of Electrical and Electronic Engineering, Chongqing University of Technology, Chongqing 400054, China
2. School of Intelligent Manufacturing and Intelligent Equipment, Chongqing Institute of Engineering, Chongqing 400056, China |
|
|
|
Abstract A multi-agent proximal policy optimization method based on a causal hypergraph neural network (MAPPO-HGNN) was proposed to address the performance degradation caused by overlapping link interference and rapidly time-varying channels in high-speed vehicular networks, with the aim of improving network throughput, latency performance, and resource utilization. A causal hypergraph was constructed to characterize the joint interference structure arising from resource sharing among multiple links. A hypergraph neural network based on spectral-normalized propagation was designed to obtain structured representations of high-order interference relationships. The resulting hypergraph embedding features were subsequently integrated into the multi-agent reinforcement learning framework, enabling adaptive spectrum resource allocation. Simulation results showed that, compared with three baseline algorithms, the proposed method achieved faster convergence and greater stability under different vehicle densities. Specifically, the average throughput and resource reuse ratio were increased by 25.2% and 15.1%, respectively, while the task latency was reduced by 16.7%. These results validated the effectiveness and robustness of the proposed method in high-speed, non-stationary vehicular networking scenarios.
|
|
Received: 08 November 2025
Published: 16 October 2026
|
|
|
| Fund: 国家自然科学基金资助项目（62301094）；重庆市技术创新与应用发展专项重大项目（CSTB2024TIAD-STX0034）；重庆市教育委员会科技研究计划资助项目（KJQN202201157，KJQN202301135）；重庆理工大学科研创新团队培育计划资助项目（2023TDZ003）. |
|
Corresponding Authors:
Chengbo YU
E-mail: 823951351@qq.com;yuchengbo@cqut.edu.cn
|
基于超图神经网络的车联网资源分配方法
针对高速车联网中链路交叠干扰与信道快速时变带来的性能退化问题，提出基于因果超图神经网络的多智能体近端策略优化方法(MAPPO-HGNN)，以提升网络吞吐量、时延性能和资源利用率. 构建因果超图以刻画多链路共享资源导致的联合干扰结构. 设计基于谱归一化传播的超图神经网络，实现高阶干扰关系的结构化表征. 将超图嵌入特征融入多智能体强化学习框架，实现频谱资源的自适应分配. 仿真结果显示，与3种基线算法相比，所提方法在不同车辆密度下均具备更快的收敛速度与更优稳定性，其中吞吐量平均提升25.2%，复用率提升15.1%，任务时延降低16.7%，验证了该方法在高速非平稳车联网场景中的有效性与鲁棒性.
关键词：
车联网(IoV),
资源分配,
超图神经网络,
因果推断,
多智能体强化学习
|
|
| [1] |
ZHANG X, LI J, ZHOU J, et al Vehicle-to-everything communication in intelligent connected vehicles: a survey and taxonomy[J]. Automotive Innovation, 2025, 8 (1): 13- 45
doi: 10.1007/s42154-024-00310-2
|
|
|
| [2] |
MEI R, WANG Z Multi-agent deep reinforcement learning-based resource allocation for cognitive radio networks[J]. IEEE Transactions on Vehicular Technology, 2025, 74 (3): 4744- 4757
doi: 10.1109/TVT.2024.3486156
|
|
|
| [3] |
MEI J, ZHENG K, ZHAO L, et al Joint radio resource allocation and control for vehicle platooning in LTE-V2V network[J]. IEEE Transactions on Vehicular Technology, 2018, 67 (12): 12218- 12230
doi: 10.1109/TVT.2018.2874722
|
|
|
| [4] |
WU Q, ZHENG J. Performance modeling of IEEE 802.11 DCF based fair channel access for vehicular-to-roadside communication in a non-saturated state [C]// Proceedings of the IEEE International Conference on Communications. Sydney: IEEE, 2014: 2575–2580.
|
|
|
| [5] |
TIAN J, LIU Q, ZHANG H, et al Multiagent deep-reinforcement-learning-based resource allocation for heterogeneous QoS guarantees for vehicular networks[J]. IEEE Internet of Things Journal, 2022, 9 (3): 1683- 1695
doi: 10.1109/JIOT.2021.3089823
|
|
|
| [6] |
HUANG J, ZHANG S, YANG F, et al Hypergraph-based interference avoidance resource management in customer-centric communication for intelligent cyber-physical transportation systems[J]. IEEE Transactions on Consumer Electronics, 2024, 70 (1): 1775- 1786
doi: 10.1109/TCE.2023.3324680
|
|
|
| [7] |
YE H, LI G Y, JUANG B F Deep reinforcement learning based resource allocation for V2V communications[J]. IEEE Transactions on Vehicular Technology, 2019, 68 (4): 3163- 3173
doi: 10.1109/TVT.2019.2897134
|
|
|
| [8] |
HUANG J, LAI X, YANG F, et al Ellipsoid-based learning for robust resource allocation with differentiated QoS in massive Internet of vehicles networks[J]. IEEE Transactions on Vehicular Technology, 2025, 74 (7): 11425- 11435
doi: 10.1109/TVT.2025.3546243
|
|
|
| [9] |
ERNEST T Z H, MADHUKUMAR A S Computation offloading in MEC-enabled IoV networks: average energy efficiency analysis and learning-based maximization[J]. IEEE Transactions on Mobile Computing, 2024, 23 (5): 6074- 6087
doi: 10.1109/TMC.2023.3315275
|
|
|
| [10] |
崔亚平, 石宏吉, 吴大鹏, 等 内容新鲜度保障的车联网多智能体缓存分发策略[J]. 通信学报, 2025, 46 (1): 52- 66
CUI Yaping, SHI Hongji, WU Dapeng, et al Multi-agent caching distribution strategy for content freshness guarantee in IoV[J]. Journal on Communications, 2025, 46 (1): 52- 66
doi: 10.11959/j.issn.1000-436x.2025013
|
|
|
| [11] |
GAO A, ZHU Z, ZHANG J, et al Matching combined heterogeneous multi-agent reinforcement learning for resource allocation in NOMA-V2X networks[J]. IEEE Transactions on Vehicular Technology, 2024, 73 (10): 15109- 15124
|
|
|
| [12] |
PARVINI M, JAVAN M R, MOKARI N, et al AoI-aware resource allocation for platoon-based C-V2X networks via multi-agent multi-task reinforcement learning[J]. IEEE Transactions on Vehicular Technology, 2023, 72 (8): 9880- 9896
doi: 10.1109/TVT.2023.3259688
|
|
|
| [13] |
宋晓勤, 张文静, 雷磊, 等 多目标联合优化的车联网动态资源分配算法[J]. 东南大学学报: 自然科学版, 2025, 55 (1): 266- 274
SONG Xiaoqin, ZHANG Wenjing, LEI Lei, et al Dynamic resource allocation algorithm for multi-objective joint optimization in Internet of vehicle[J]. Journal of Southeast University: Natural Science Edition, 2025, 55 (1): 266- 274
|
|
|
| [14] |
JI Y, WANG Y, ZHAO H, et al Multi-agent reinforcement learning resources allocation method using dueling double deep Q-network in vehicular networks[J]. IEEE Transactions on Vehicular Technology, 2023, 72 (10): 13447- 13460
doi: 10.1109/TVT.2023.3275546
|
|
|
| [15] |
ZHANG X, ZHANG H, TANG H, et al A scalable mean-field MARL framework for multi-objective V2X resource allocation[J]. IEEE Transactions on Intelligent Vehicles, 2025, 10 (2): 1071- 1086
doi: 10.1109/TIV.2024.3422506
|
|
|
| [16] |
CHEN C, WANG W, LIU Z, et al RLFN-VRA: reinforcement learning-based flexible numerology V2V resource allocation for 5G NR V2X networks[J]. IEEE Transactions on Intelligent Vehicles, 2025, 10 (2): 1379- 1390
doi: 10.1109/TIV.2024.3427399
|
|
|
| [17] |
HUANG J, YANG C, ZHANG S, et al Reinforcement learning based resource management for 6G-enabled mIoT with hypergraph interference model[J]. IEEE Transactions on Communications, 2024, 72 (7): 4179- 4192
doi: 10.1109/TCOMM.2024.3372892
|
|
|
| [18] |
YANG J, MA Y, XIAO Z, et al Joint access selection, computation offloading, and resource allocation in LEO ubiquitous edge computing networks[J]. IEEE Internet of Things Journal, 2025, 12 (23): 51746- 51760
doi: 10.1109/JIOT.2025.3616653
|
|
|
| [19] |
MEI J, ZHENG K, ZHAO L, et al A latency and reliability guaranteed resource allocation scheme for LTE V2V communication systems[J]. IEEE Transactions on Wireless Communications, 2018, 17 (6): 3850- 3860
doi: 10.1109/TWC.2018.2816942
|
|
|
| [20] |
HUANG Q, YI X, QI F, et al Enhancing 5G V2X URLLC broadcast/multicast services with FL-based wireless resource allocation[J]. IEEE Transactions on Broadcasting, 2025, 71 (2): 384- 396
doi: 10.1109/TBC.2025.3541887
|
|
|
| [21] |
ALWARAFY A, ABDALLAH M, ÇIFTLER B S, et al The frontiers of deep reinforcement learning for resource management in future wireless HetNets: techniques, challenges, and research directions[J]. IEEE Open Journal of the Communications Society, 2022, 3: 322- 365
doi: 10.1109/OJCOMS.2022.3153226
|
|
|
| [22] |
RUAN Z, YU C. Causality-guided exploration for multi-agent reinforcement learning [C]// Proceedings of the IEEE International Conference on Agents. Wollongong: IEEE, 2024: 56–59.
|
|
|
| [23] |
ARANA-CATANIA M, SONEE A, KHAN A M, et al Explainable reinforcement and causal learning for improving trust to 6G stakeholders[J]. IEEE Open Journal of the Communications Society, 2025, 6: 4101- 4125
doi: 10.1109/OJCOMS.2025.3563415
|
|
|
| [24] |
LIANG L, YE H, LI G Y Spectrum sharing in vehicular networks based on multi-agent reinforcement learning[J]. IEEE Journal on Selected Areas in Communications, 2019, 37 (10): 2282- 2292
doi: 10.1109/JSAC.2019.2933962
|
|
|
| [25] |
ZENG J, KUANG Z, CHEN R, et al Delay-sensitive dependent tasks offloading and resource allocation in VEC: a deep-reinforcement learning approach[J]. IEEE Internet of Things Journal, 2025, 12 (16): 34190- 34203
doi: 10.1109/JIOT.2025.3577449
|
|
|
| [26] |
VU H V, FARZANULLAH M, LIU Z, et al. Multi-agent reinforcement learning for channel assignment and power allocation in platoon-based C-V2X systems [C]// Proceedings of the IEEE 95th Vehicular Technology Conference. Helsinki: IEEE, 2022: 1–5.
|
|
|
| [27] |
LIU X, LIU J, LI W Truthful mechanism for resource allocation and pricing in vehicle-assisted mobile edge computing[J]. IEEE Transactions on Vehicular Technology, 2025, 74 (5): 8171- 8186
doi: 10.1109/TVT.2025.3526935
|
|
|
| [28] |
3GPP. Study on LTE-based V2X services: TR 36.885 [S]. Valbonne: 3GPP, 2016.
|
|
|
| [29] |
FRIIS H T A note on a simple transmission formula[J]. Proceedings of the IRE, 1946, 34 (5): 254- 256
doi: 10.1109/JRPROC.1946.234568
|
|
|
| [30] |
LI Y, WANG N, BAI N, et al. Resource allocation for V2V-enabled vehicular communications based on hypergraph partition [C]// Proceedings of the International Conference on Microwave and Millimeter Wave Technology. Qingdao: IEEE, 2023: 1–3.
|
|
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
| |
Shared |
|
|
|
|
| |
Discussed |
|
|
|
|
