Intelligent Reflecting Surface Configurations for Smart Radio Using Deep Reinforcement Learning

被引:62
作者
Wang, Wei [1 ]
Zhang, Wei [2 ]
机构
[1] Peng Cheng Lab, Shenzhen 518000, Peoples R China
[2] Univ New South Wales, Sch Elect Engn & Telecommun, Sydney, NSW 2052, Australia
基金
澳大利亚研究理事会;
关键词
Wireless communication; Channel estimation; Wireless sensor networks; Reinforcement learning; Adaptation models; MIMO communication; Training; Deep reinforcement learning; extremum seeking control; intelligent reflecting surface; model-free control; EXTREMUM SEEKING CONTROL; CHANNEL ESTIMATION; SYSTEMS; CONVERGENCE;
D O I
10.1109/JSAC.2022.3180787
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
Intelligent reflecting surface (IRS) is envisioned to change the paradigm of wireless communications from "adapting to wireless channels" to "changing wireless channels". However, current IRS configuration schemes, consisting of sub-channel estimation and passive beamforming in sequence, conform to the conventional model-based design philosophies and are difficult to be realized practically in the complex radio environment. To create the smart radio environment, we propose a model-free design of IRS control that is independent of the sub-channel channel state information (CSI) and requires the minimum interaction between IRS and the wireless communication system. We firstly model the control of IRS as a Markov decision process (MDP) and apply deep reinforcement learning (DRL) to perform real-time coarse phase control of IRS. Then, we apply extremum seeking control (ESC) as the fine phase control of IRS. Finally, by updating the frame structure, we integrate DRL and ESC in the model-free control of IRS to improve its adaptivity to different channel dynamics. Numerical results show the superiority of our proposed joint DRL and ESC scheme and verify its effectiveness in model-free IRS control without sub-channel CSI.
引用
收藏
页码:2335 / 2346
页数:12
相关论文
共 50 条
[1]  
[Anonymous], 2006, Fundamentals of Wireless Communication
[2]  
Ariyur K. B., 2003, Real-Time Optimization by Extremum-Seeking Control
[3]   Deep Reinforcement Learning A brief survey [J].
Arulkumaran, Kai ;
Deisenroth, Marc Peter ;
Brundage, Miles ;
Bharath, Anil Anthony .
IEEE SIGNAL PROCESSING MAGAZINE, 2017, 34 (06) :26-38
[4]   Extremum seeking control based on phasor estimation [J].
Atta, Khalid Tourkey ;
Johansson, Andreas ;
Gustafsson, Thomas .
SYSTEMS & CONTROL LETTERS, 2015, 85 :37-45
[5]   A Deep Learning Based Modeling of Reconfigurable Intelligent Surface Assisted Wireless Communications for Phase Shift Configuration [J].
Sheen B. ;
Yang J. ;
Feng X. ;
Chowdhury M.M.U. .
IEEE Open Journal of the Communications Society, 2021, 2 :262-272
[6]  
Carnevale D., 2010, PHYS CONTROL EMERGEN, P321
[7]  
Chiya Zhang, 2021, Journal of Communications and Information Networks, V6, P197, DOI 10.23919/JCIN.2021.9549117
[8]   Coding metamaterials, digital metamaterials and programmable metamaterials [J].
Cui, Tie Jun ;
Qi, Mei Qing ;
Wan, Xiang ;
Zhao, Jie ;
Cheng, Qiang .
LIGHT-SCIENCE & APPLICATIONS, 2014, 3 :e218-e218
[9]  
Engheta N., 2016, METAMATERIALS PHYS E
[10]  
Fangfang Liu, 2021, Journal of Communications and Information Networks, V6, P101, DOI 10.23919/JCIN.2021.9475120