Reconfigurable Intelligent Surface Assisted Multiuser MISO Systems Exploiting Deep Reinforcement Learning

被引:515
|
作者
Huang, Chongwen [1 ]
Mo, Ronghong [1 ]
Yuen, Chau [1 ]
机构
[1] Singapore Univ Technol & Design, Engn Prod Dev EPD Pillar, Singapore 487372, Singapore
关键词
Array signal processing; MIMO communication; Optimization; Wireless communication; MISO communication; Antenna arrays; Receivers; Reconfigurable intelligent surface; Massive MIMO; 6G; smart radio environment; beamforming matrix; phase shift matrix; deep reinforcement learning; MASSIVE MIMO; WIRELESS COMMUNICATION; NETWORKS; DESIGN;
D O I
10.1109/JSAC.2020.3000835
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
Recently, the reconfigurable intelligent surface (RIS), benefited from the breakthrough on the fabrication of programmable meta-material, has been speculated as one of the key enabling technologies for the future six generation (6G) wireless communication systems scaled up beyond massive multiple input multiple output (Massive-MIMO) technology to achieve smart radio environments. Employed as reflecting arrays, RIS is able to assist MIMO transmissions without the need of radio frequency chains resulting in considerable reduction in power consumption. In this paper, we investigate the joint design of transmit beamforming matrix at the base station and the phase shift matrix at the RIS, by leveraging recent advances in deep reinforcement learning (DRL). We first develop a DRL based algorithm, in which the joint design is obtained through trial-and-error interactions with the environment by observing predefined rewards, in the context of continuous state and action. Unlike the most reported works utilizing the alternating optimization techniques to alternatively obtain the transmit beamforming and phase shifts, the proposed DRL based algorithm obtains the joint design simultaneously as the output of the DRL neural network. Simulation results show that the proposed algorithm is not only able to learn from the environment and gradually improve its behavior, but also obtains the comparable performance compared with two state-of-the-art benchmarks. It is also observed that, appropriate neural network parameter settings will improve significantly the performance and convergence rate of the proposed algorithm.
引用
收藏
页码:1839 / 1850
页数:12
相关论文
共 50 条
  • [21] Active Reconfigurable Intelligent Surface-Assisted MISO Integrated Sensing and Communication Systems for Secure Operation
    Salem, A. Abdelaziz
    Ismail, Mahmoud H. H.
    Ibrahim, Ahmed S. S.
    [J]. IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2023, 72 (04) : 4919 - 4931
  • [22] Reconfigurable Intelligent Surface-assisted Classification of Modulations using Deep Learning
    Lodro, Mir
    Taghvaee, Hamidreza
    Gros, Jean-Baptiste
    Greedy, Steve
    Lerosey, Geofrroy
    Gradoni, Gabriele
    [J]. 2022 3RD URSI ATLANTIC AND ASIA PACIFIC RADIO SCIENCE MEETING (AT-AP-RASC), 2022,
  • [23] Accelerated PARAFAC-Based Channel Estimation for Reconfigurable Intelligent Surface-Assisted MISO Systems
    Xiao, Haoqi
    Deng, Honggui
    Guo, Aimin
    Qian, Yuyan
    Peng, Chengzuo
    Zhang, Yinhao
    [J]. SENSORS, 2022, 22 (19)
  • [24] Energy Harvesting Reconfigurable Intelligent Surface for UAV Based on Robust Deep Reinforcement Learning
    Peng, Haoran
    Wang, Li-Chun
    [J]. IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2023, 22 (10) : 6826 - 6838
  • [25] A Deep Reinforcement Learning Approach to Two-Timescale Transmission for RIS-Aided Multiuser MISO systems
    Zhang, Huaqian
    Li, Xiao
    Gao, Ning
    Yi, Xinping
    Jin, Shi
    [J]. IEEE WIRELESS COMMUNICATIONS LETTERS, 2023, 12 (08) : 1444 - 1448
  • [26] Simultaneous Transmission and Reflection Reconfigurable Intelligent Surface Assisted Secrecy MISO Networks
    Niu, Hehao
    Chu, Zheng
    Zhou, Fuhui
    Zhu, Zhengyu
    [J]. IEEE COMMUNICATIONS LETTERS, 2021, 25 (11) : 3498 - 3502
  • [27] Deep Reinforcement Learning for RIS-Aided Multiuser MISO System with Hardware Impairments
    Ma, Wenjie
    Zhuo, Liuchang
    Li, Luchu
    Liu, Yuhao
    Ren, Hong
    [J]. APPLIED SCIENCES-BASEL, 2022, 12 (14):
  • [28] Deep Bidirectional Learning Based Enhanced Outage Probability for Aerial Reconfigurable Intelligent Surface Assisted Communication Systems
    Rahman, Md Habibur
    Sejan, Mohammad Abrar Shakil
    Aziz, Md Abdul
    Tabassum, Rana
    Song, Hyoung-Kyu
    [J]. MATHEMATICS, 2024, 12 (11)
  • [29] Active Reconfigurable Intelligent Surface-Assisted Mainlobe Wideband RFI Mitigation With Deep Reinforcement Learning for a Large Reflector Antenna
    Peng, Junhui
    Cao, Hailin
    Fan, Jin
    Zhang, Zhengjie
    Wu, Decheng
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2024, 62
  • [30] Deep Reinforcement Learning-Driven Reconfigurable Intelligent Surface-Assisted Radio Surveillance With a Fixed-Wing UAV
    Yuan, Xin
    Hu, Shuyan
    Ni, Wei
    Wang, Xin
    Jamalipour, Abbas
    [J]. IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2023, 18 : 4546 - 4560