Multi-Agent Reinforcement Learning for Channel Assignment and Power Allocation in Platoon-Based C-V2X Systems

被引:7
作者
Vu, Hung V. [1 ]
Farzanullah, Mohammad [2 ]
Liu, Zheyu [2 ]
Nguyen, Duy H. N. [3 ]
Morawski, Robert [2 ]
Le-Ngoc, Tho [2 ]
机构
[1] Huawei Technol Canada, Ottawa, ON, Canada
[2] McGill Univ, Dept Elect & Comp Engn, Montreal, PQ, Canada
[3] San Diego State Univ, Dept Elect & Comp Engn, San Diego, CA USA
来源
2022 IEEE 95TH VEHICULAR TECHNOLOGY CONFERENCE (VTC2022-SPRING) | 2022年
基金
加拿大自然科学与工程研究理事会;
关键词
Vehicle-to-everything; cellular networks; reinforcement learning; resource allocation;
D O I
10.1109/VTC2022-Spring54318.2022.9860518
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
We consider the problem of joint channel assignment and power allocation in underlaid cellular vehicular-to-everything (C-V2X) systems where multiple vehicle-to-network (V2N) uplinks share the time-frequency resources with multiple vehicle-to-vehicle (V2V) platoons that enable groups of connected and autonomous vehicles to travel closely together. Due to the nature of high user mobility in vehicular environment, traditional centralized optimization approach relying on global channel information might not be viable in C-V2X systems with large number of users. Utilizing a multi-agent reinforcement learning (RL) approach, we propose a distributed resource allocation (RA) algorithm to overcome this challenge. Specifically, we model the RA problem as a multi-agent system. Based solely on the local channel information, each platoon leader, acting as an agent, collectively interacts with each other and accordingly selects the optimal combination of sub-band and power level to transmit its signals. Toward this end, we utilize the double deep Q-learning algorithm to jointly train the agents under the objectives of simultaneously maximizing the sum-rate of V2N links and satisfying the packet delivery probability of each V2V link in a desired latency limitation. Simulation results show that our proposed RL-based algorithm provides a close performance compared to that of the well-known exhaustive search algorithm.
引用
收藏
页数:5
相关论文
共 13 条
  • [1] [Anonymous], 2016, document TR 36.885 V14.0.0.
  • [2] [Anonymous], 2018, 22886 TR
  • [3] LTE for Vehicular Networking: A Survey
    Araniti, Giuseppe
    Campolo, Claudia
    Condoluci, Massimo
    Iera, Antonio
    Molinaro, Antonella
    [J]. IEEE COMMUNICATIONS MAGAZINE, 2013, 51 (05) : 148 - 157
  • [4] Foerster JN, 2017, PR MACH LEARN RES, V70
  • [5] Spectrum Sharing in Vehicular Networks Based on Multi-Agent Reinforcement Learning
    Liang, Le
    Ye, Hao
    Li, Geoffrey Ye
    [J]. IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS, 2019, 37 (10) : 2282 - 2292
  • [6] Graph-Based Resource Sharing in Vehicular Communication
    Liang, Le
    Xie, Shijie
    Li, Geoffrey Ye
    Ding, Zhi
    Yu, Xingxing
    [J]. IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2018, 17 (07) : 4579 - 4592
  • [7] Resource Allocation for D2D-Enabled Vehicular Communications
    Liang, Le
    Li, Geoffrey Ye
    Xu, Wei
    [J]. IEEE TRANSACTIONS ON COMMUNICATIONS, 2017, 65 (07) : 3186 - 3197
  • [8] Human-level control through deep reinforcement learning
    Mnih, Volodymyr
    Kavukcuoglu, Koray
    Silver, David
    Rusu, Andrei A.
    Veness, Joel
    Bellemare, Marc G.
    Graves, Alex
    Riedmiller, Martin
    Fidjeland, Andreas K.
    Ostrovski, Georg
    Petersen, Stig
    Beattie, Charles
    Sadik, Amir
    Antonoglou, Ioannis
    King, Helen
    Kumaran, Dharshan
    Wierstra, Daan
    Legg, Shane
    Hassabis, Demis
    [J]. NATURE, 2015, 518 (7540) : 529 - 533
  • [9] Radio Resource Management for D2D-Based V2V Communication
    Sun, Wanlu
    Strom, Erik G.
    Brannstrom, Fredrik
    Sou, Kin Cheong
    Sui, Yutao
    [J]. IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2016, 65 (08) : 6636 - 6650
  • [10] van Hasselt H, 2016, AAAI CONF ARTIF INTE, P2094