In this paper, the equivalence between the rate maximization and weighted minimum mean square error (WMMSE) minimization problems is utilized to design the hybrid beamforming scheme for millimeter wave relay systems. A deep unfolding method is proposed based on the structure of the WMMSE iterative algorithm, and the back propagation algorithm is updated based on the generalized chain rule of complex matrix gradients. Simulation results show that the proposed method has the satisfactory generalization ability, and prevails existing methods both in the spectral efficiency and running time.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Hybrid Beamforming for Millimeter Wave Relay Systems: A Deep Unfolding Approach


    Contributors:
    Luo, Zhen (author) / Wang, Xinyu (author) / Xie, Fu (author) / Liu, Hongqing (author)


    Publication date :

    2024-06-24


    Size :

    473457 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Hybrid Beamforming in mmWave MIMO-OFDM Systems via Deep Unfolding

    Chen, Kuan-Yuan / Chang, Hsin-Yuan / Chang, Ronald Y. 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


    Hybrid Beamforming for Broadband Millimeter Wave Massive MIMO Systems

    Chen, Rui / Xu, Hui / Li, Changle et al. | IEEE | 2018


    User-Directed Analog Beamforming for Multiuser Millimeter-Wave Hybrid Array Systems

    Zhang, J. Andrew / Li, Hang / Huang, Xiaojing et al. | IEEE | 2017


    Constrained-SVD based Hybrid Beamforming Design for Millimeter-Wave Communications

    Zilli, Guilherme Martignago / Zhu, Wei-Ping | IEEE | 2020