Multiple Residual Dense Networks for Reconfigurable Intelligent Surfaces Cascaded Channel Estimation

被引:33
作者
Jin, Yu [1 ,2 ]
Zhang, Jiayi [1 ,2 ]
Huang, Chongwen [3 ]
Yang, Liang [4 ]
Xiao, Huahua [5 ,6 ]
Ai, Bo [7 ,8 ,9 ,10 ]
Wang, Zhiqin [11 ]
机构
[1] Beijing Jiaotong Univ, Sch Elect & Informat Engn, Beijing 100044, Peoples R China
[2] Beijing Jiaotong Univ, Frontiers Sci Ctr Smart High Speed Railway Syst, Beijing 100044, Peoples R China
[3] Zhejiang Univ, Prov Key Lab Informat Proc Commun & Networking, Hangzhou 310007, Zhejiang, Peoples R China
[4] Hunan Univ, Coll Comp Sci & Elect Engn, Changsha 410082, Peoples R China
[5] ZTE Corp, Shenzhen 518057, Peoples R China
[6] State Key Lab Mobile Network & Mobile Multimedia, Shenzhen 518057, Peoples R China
[7] Beijing Jiaotong Univ, State Key Lab Rail Traff Control & Safety, Beijing 100044, Peoples R China
[8] Zhengzhou Univ, Frontiers Sci Ctr Smart High Speed Railway Syst, Zhengzhou 450001, Peoples R China
[9] Zhengzhou Univ, Henan Joint Int Res Lab Intelligent Networking &, Zhengzhou 450001, Peoples R China
[10] Peng Cheng Lab, Res Ctr Networks & Commun, Shenzhen 518055, Peoples R China
[11] Acad Informat & Commun Technol, Beijing 100191, Peoples R China
基金
北京市自然科学基金; 中国国家自然科学基金;
关键词
Channel estimation; Antennas; Noise reduction; Training; MIMO communication; Estimation; Wireless communication; deep learning; multiple residual dense network; reconfigurable intelligent surface;
D O I
10.1109/TVT.2021.3132305
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
Reconfigurable intelligent surface (RIS) constitutes an essential and promising paradigm that relies programmable wireless environment and provides capability for space-intensive communications, due to the use of low-cost massive reflecting elements over the entire surfaces of man-made structures. However, accurate channel estimation is a fundamental technical prerequisite to achieve the huge performance gains from RIS. By leveraging the low rank structure of RIS channels, three practical residual neural networks, named convolutional blind denoising network, convolutional denoising generative adversarial networks and multiple residual dense network, are proposed to obtain accurate channel state information, which can reflect the impact of different methods on the estimation performance. Simulation results reveal the evolution direction of these three methods and reveal their superior performance compared with existing benchmark schemes.
引用
收藏
页码:2134 / 2139
页数:6
相关论文
共 17 条
[1]  
Chen J., 2019, CoRR abs/1904.02144
[2]   Cascaded Channel Estimation for Large Intelligent Metasurface Assisted Massive MIMO [J].
He, Zhen-Qing ;
Yuan, Xiaojun .
IEEE WIRELESS COMMUNICATIONS LETTERS, 2020, 9 (02) :210-214
[3]   Reconfigurable Intelligent Surfaces for Energy Efficiency in Wireless Communication [J].
Huang, Chongwen ;
Zappone, Alessio ;
Alexandropoulos, George C. ;
Debbah, Merouane ;
Yuen, Chau .
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2019, 18 (08) :4157-4170
[4]   Channel Estimation for mmWave Massive MIMO With Convolutional Blind Denoising Network [J].
Jin, Yu ;
Zhang, Jiayi ;
Ai, Bo ;
Zhang, Xiaodan .
IEEE COMMUNICATIONS LETTERS, 2020, 24 (01) :95-98
[5]   GRDN:Grouped Residual Dense Network for Real Image Denoising and GAN-based Real-world Noise Modeling [J].
Kim, Dong-Wook ;
Chung, Jae Ryun ;
Jung, Seung-Won .
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW 2019), 2019, :2086-2094
[6]  
Lin J., 2019, P IEEE 2 INT C BIG D
[7]   Deep Residual Network Empowered Channel Estimation for IRS-Assisted Multi-User Communication Systems [J].
Liu, Chang ;
Liu, Xuemeng ;
Ng, Derrick Wing Kwan ;
Yuan, Jinhong .
IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (ICC 2021), 2021,
[8]   Deep Denoising Neural Network Assisted Compressive Channel Estimation for mmWave Intelligent Reflecting Surfaces [J].
Liu, Shicong ;
Gao, Zhen ;
Zhang, Jun ;
Di Renzo, Marco ;
Alouini, Mohamed-Slim .
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2020, 69 (08) :9223-9228
[9]   Deep Learning for Large Intelligent Surfaces in Millimeter Wave and Massive MIMO Systems [J].
Taha, Abdelrahman ;
Alrabeiah, Muhammad ;
Alkhateeb, Ahmed .
2019 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM), 2019,
[10]   Massive MIMO Channel Estimation for Mill meter Wave Systems via Matrix Completion [J].
Vlachos, Evangelos ;
Alexandropoulos, George C. ;
Thompson, John .
IEEE SIGNAL PROCESSING LETTERS, 2018, 25 (11) :1675-1679