In this paper, we explore the integration of a reconfigurable intelligent surface (RIS) with a multi-antenna base station (BS) for downlink multi-user multiple-input-single-output (MU-MISO) systems. We aim to enhance energy efficiency (EE) by jointly optimizing beamforming and phase shifts at the BS and RIS, respectively, while ensuring each mobile user meets their link budget requirements. The resulting optimization problem is inherently non-convex. To address this challenge, we employ proximal policy optimization (PPO), known for efficiently managing non-convex problems and reducing training overhead in continuous action spaces through a clip factor. Furthermore, by leveraging deep neural networks (DNN), the proposed PPO-based solution provides the optimum values for the beamforming at the BS and the phase shift at the RIS, respectively. Finally, we demonstrate the effectiveness and accuracy of the proposed PPO-based algorithm through an extensive simulation campaign, comparing its performance against baseline methods (i.e., fractional programming (FP) and deep deterministic policy gradient (DDPG)). The results show that our proposed PPO-based algorithm outperforms the considered baseline approaches (i.e., FP and DDPG) in terms of EE by 34.2% and 15.8%, respectively.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    PPO-Based Energy Efficiency Maximization For RIS-Assisted Multi-User Miso Systems


    Contributors:


    Publication date :

    2024-10-07


    Size :

    543437 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    Robust Precoding for FDD MISO Systems via Minorization Maximization

    Amor, Donia Ben / Joham, Michael / Utschick, Wolfgang | IEEE | 2024


    Sum-Rate Maximization of Symbiotic Multi-V2X MISO and Multi-RIS BackCom with Imperfections

    Asiedu, Derek K. P. / Ofori-Amanfo, Kofi A. / Benjillali, Mustapha et al. | IEEE | 2024


    Energy Efficiency Maximization for Hybrid NOMA Strategy in Multi-User MEC Networks

    Huang, Wenqi / Wang, Kaidi / Ding, Zhiguo | IEEE | 2024


    Energy Efficient Beamforming for Multi-Cell MISO SWIPT Systems

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