Hybrid Spectrum Access for V2V Heterogeneous Networks with Deep Reinforcement Learning

被引:1
|
作者
Huang, Jingfei [1 ]
Peng, Jingyi [2 ]
Xiang, Honglin [1 ]
Li, Lingjie [1 ]
Yang, Yang [1 ]
机构
[1] Beijing Univ Posts & Telecommun, Sch Artificial Intelligence, Beijing 100876, Peoples R China
[2] China Ind Control Syst Cyber Emergency Response T, Beijing 100040, Peoples R China
来源
2022 14TH INTERNATIONAL CONFERENCE ON WIRELESS COMMUNICATIONS AND SIGNAL PROCESSING, WCSP | 2022年
基金
中国国家自然科学基金;
关键词
Heterogeneous network; hybrid spectrum access; V2V communication; deep reinforcement learning;
D O I
10.1109/WCSP55476.2022.10039356
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
This paper studies the hybrid spectrum access for cellular vehicle-to-vehicle (V2V) heterogeneous networks (Het-Nets) exploiting deep reinforcement learning (DRL) technology. In the system, macro cell users (M-UEs), V2V clusters (V-Clusters) and V2V nodes are distributed in the time-division duplex (TDD) cellular networks, where all users share the cellular uplink resources for spectrum access. M-UEs and V-Clusters adopt orthogonal access patterns. V2V nodes expect to obtain an optimal strategy to reuse other users' resource for access while preventing other users from serious interference, which is difficult due to the limited information of other users' access patterns. Thus, DRL technology is used to train V2V nodes in an unsupervised way, where the spectrum access can be optimized without any prior information. Specifically, a double deep Q-network (DDQN) based hybrid spectrum access (D2HSA) algorithm is designed for maximizing the sum throughput of the HetNets, which makes the V2V nodes intelligently select suitable frames for spectrum access. Furthermore, in order to improve the stability of individual throughput for V2V nodes, the proposed algorithm is adjusted by considering stability in the design of the objective function. Last, the experiment results illustrate that our proposed scheme could reach an optimal throughput referring to the theoretic limit for different cases, and the performance greatly outperforms the scheme relying on the cooperation of base station.
引用
收藏
页码:1091 / 1095
页数:5
相关论文
共 50 条
  • [21] Velocity forecasts using a combined deep learning model in hybrid electric vehicles with V2V and V2I communication
    JiaZheng Pei
    YiXin Su
    DanHong Zhang
    Yue Qi
    ZhiWen Leng
    Science China Technological Sciences, 2020, 63 : 55 - 64
  • [22] Velocity forecasts using a combined deep learning model in hybrid electric vehicles with V2V and V2I communication
    Pei, JiaZheng
    Su, YiXin
    Zhang, DanHong
    Qi, Yue
    Leng, ZhiWen
    SCIENCE CHINA-TECHNOLOGICAL SCIENCES, 2020, 63 (01) : 55 - 64
  • [23] Velocity forecasts using a combined deep learning model in hybrid electric vehicles with V2V and V2I communication
    PEI JiaZheng
    SU YiXin
    ZHANG DanHong
    QI Yue
    LENG ZhiWen
    Science China(Technological Sciences), 2020, 63 (01) : 55 - 64
  • [24] Deep Reinforcement Learning for Dynamic Spectrum Access in Wireless Networks
    Xu, Y.
    Yu, J.
    Headley, W. C.
    Buehrer, R. M.
    2018 IEEE MILITARY COMMUNICATIONS CONFERENCE (MILCOM 2018), 2018, : 207 - 212
  • [25] A Joint Scheduling and Power Control Scheme for Hybrid I2V/V2V Networks
    Nguyen, Bach Long
    Ngo, Duy Trong
    Dao, Minh N.
    Duong, Quang-Thang
    Okada, Minoru
    IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2020, 69 (12) : 15668 - 15681
  • [26] A Joint Power and Bandwidth Allocation Method Based on Deep Reinforcement Learning for V2V Communications in 5G
    Hu, Xin
    Xu, Sujie
    Wang, Libing
    Wang, Yin
    Liu, Zhijun
    Xu, Lexi
    Li, You
    Wang, Weidong
    CHINA COMMUNICATIONS, 2021, 18 (07) : 25 - 35
  • [27] A Hybrid V2I and V2V Approach for Urban Traffic Management in Vehicular Networks
    Loureco, Massilon
    Souza, Fernanda S. H.
    Silva, Cristiano M.
    Meneguette, Rodolfo I.
    Guidoni, Daniel L.
    2019 IEEE LATIN-AMERICAN CONFERENCE ON COMMUNICATIONS (IEEE LATINCOM), 2019,
  • [28] A Joint Power and Bandwidth Allocation Method Based on Deep Reinforcement Learning for V2V Communications in 5G
    Xin Hu
    Sujie Xu
    Libing Wang
    Yin Wang
    Zhijun Liu
    Lexi Xu
    You Li
    Weidong Wang
    中国通信, 2021, 18 (07) : 25 - 35
  • [29] Delay Analysis and Message Delivery Strategy in Hybrid V2I/V2V Networks
    Ni, Yuanzhi
    He, Jianping
    Cai, Lin
    Bo, Yuming
    2016 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM), 2016,
  • [30] A Reinforcement Learning-Based Congestion Control Approach for V2V Communication in VANET
    Liu, Xiaofeng
    St Amour, Ben
    Jaekel, Arunita
    APPLIED SCIENCES-BASEL, 2023, 13 (06):