In multi-user multi-input single-output (MU-MISO) cellular networks, beamforming is an effective way to manage the inter-cell interference and intra-cell interference, and improve the achievable rate. However, finding the optional beamforming solution needs a centralized structure, which may be impractical in realistic scenario. In this paper, a distributed deep reinforcement learning (DRL) based beamforming algorithm is proposed in which each base station (BS) uses DRL to select the beamformers for its intended users in each cell. Besides, the channel orthogonality measure among intended users, on behalf of the intra-cell interference, is used as the state element of the DRL. Moreover, by applying the proposed method, the number of action elements can be reduced, thus the training complexity decreased. Compared with the benchmark algorithm, the simulation results demonstrate that this scheme could improve the system achievable rate. In a word, this paper provides another way for optimizing the beamforming problem in MU-MISO systems.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Beamforming in Multi-User MISO Cellular Networks with Deep Reinforcement Learning


    Contributors:
    Chen, Hongchao (author) / Zheng, Zhe (author) / Liang, Xiaohui (author) / Liu, Yupu (author) / Zhao, Yi (author)


    Publication date :

    2021-04-01


    Size :

    2299771 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    A Deep Reinforcement Learning based Analog Beamforming Approach in Downlink MISO Systems

    Zhou, Hang / Wang, Xiaoyan / Umehira, Masahiro et al. | IEEE | 2022



    Deep reinforcement learning for hybrid beamforming in multi-user millimeter wave wireless systems

    Lizarraga, Enrique M. / Maggio, Gabriel N. / Dowhuszko, Alexis A. | IEEE | 2021


    Energy Efficient Beamforming for Multi-Cell MISO SWIPT Systems

    Jang, Seokju / Lee, Hoon / Kang, Seowoo et al. | IEEE | 2018


    Transmit Beamforming Designs for Secure Transmission in MISO-NOMA Networks

    Zhang, Yanbo / Yang, Zheng / Cui, Jingjing et al. | IEEE | 2022