Millimeter wave (mmWave) with abundant spectrum resources can realize high-rate communications in vehicular networks. However, the mobility of vehicles and the blocking effect of mmWave propagation bring new challenges to communication security. Cooperative communication is envisioned as a promising physical layer security (PLS) approach to enhance the secrecy performance, but it will induce extra energy consumption of vehicles. This paper proposes a deep recurrent reinforcement learning (DRRL)-based energy-efficient cooperative secure transmission scheme in mmWave vehicular networks, where eavesdropping vehicles attempt to intercept the multi-user downlink communications. We jointly design the mmWave beam allocation, the cooperative nodes selection, and the transmit power of vehicles. Specifically, the mmWave base station selects idle vehicles as relays to overcome the severe blocking attenuation of legitimate transmissions and controls the transmit power to reduce energy consumption. Moreover, to ensure secure transmission, a cooperative vehicle is selected to transmit jamming signals to the eavesdropping vehicles while the legitimate users are not disturbed. We conduct comprehensive interference analysis for both direct transmission and relay-aided transmission, and derive the theoretical expressions for the secrecy capacity. We then design the Dueling Double Deep Recurrent Q-Network (D3RQN) learning algorithm to maximize the total secrecy capacity subject to the energy consumption constraint. We set the energy consumption punishment mechanism to avoid relay vehicles consuming too much power for forwarding signals. We demonstrate that the proposed scheme can rapidly adapt to the highly dynamic vehicular networks and effectively improve secrecy performance while reducing the energy consumption of vehicles.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Energy-Efficient Cooperative Secure Communications in mmWave Vehicular Networks Using Deep Recurrent Reinforcement Learning


    Contributors:
    Ju, Ying (author) / Gao, Zipeng (author) / Wang, Haoyu (author) / Liu, Lei (author) / Pei, Qingqi (author) / Dong, Mianxiong (author) / Mumtaz, Shahid (author) / Leung, Victor C. M. (author)

    Published in:

    Publication date :

    2024-10-01


    Size :

    2814381 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Secure NOMA-Assisted Multi-User mmWave Vehicular Communications Using Artificial Noise

    Yan, Yiting / Ju, Ying / Tian, Suheng et al. | IEEE | 2024


    mmWave massive MIMO vehicular communications

    Cheng, Xiang / Gao, Shijian / Yang, Liuqing | TIBKAT | 2023


    Light-weight Machine Learning for mmWave Vehicular Communications

    Wang, Yitu / Nakachi, Takayuki | IEEE | 2020


    Cooperative perception in vehicular networks using multi-agent reinforcement learning

    Abdel-Aziz, M. K. (Mohamed K.) / Samarakoon, S. (Sumudu) / Perfecto, C. (Cristina) et al. | BASE | 2021

    Free access