Deep Residual Network Empowered Channel Estimation for IRS-Assisted Multi-User Communication Systems

被引:15
作者
Liu, Chang [1 ]
Liu, Xuemeng [2 ]
Ng, Derrick Wing Kwan [1 ]
Yuan, Jinhong [1 ]
机构
[1] Univ New South Wales, Sch Elect Engn & Telecommun, Sydney, NSW, Australia
[2] Univ Sydney, Sch Elect & Informat Engn, Sydney, NSW, Australia
来源
IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (ICC 2021) | 2021年
基金
澳大利亚研究理事会; 中国国家自然科学基金;
关键词
CNN;
D O I
10.1109/ICC42927.2021.9500708
中图分类号
TN [电子技术、通信技术];
学科分类号
0809 ;
摘要
Channel estimation is of great importance in realizing practical intelligent reflecting surface-assisted multi-user communication (IRS-MC) systems. However, different from traditional communication systems, an IRS-MC system generally involves a cascaded channel with a sophisticated statistical distribution, which hinders the implementations of the Bayesian estimators. To further improve the channel estimation performance, in this paper, we model the channel estimation as a denoising problem and adopt a data-driven approach to realize the channel estimation. Specifically, we propose a convolutional neural network (CNN)-based deep residual network (CDRN) to implicitly learn the residual noise for recovering the channel coefficients from the noisy pilot-based observations. In the proposed CDRN, a CNN denoising block equipped with an element-wise subtraction structure is designed to exploit both the spatial features of the noisy channel matrices and the additive nature of the noise simultaneously, which further improves the estimation accuracy. Simulation results demonstrate that the proposed method can almost achieve the same estimation accuracy as that of the optimal minimum mean square error (MMSE) estimator requiring the knowledge of the channel distribution.
引用
收藏
页数:7
相关论文
共 25 条
[1]   Training-based MIMO channel estimation: A study of estimator tradeoffs and optimal training signals [J].
Biguesh, M ;
Gershman, AB .
IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2006, 54 (03) :884-893
[2]  
Chen Jianbo, 2019, CoRR abs/1904.02144
[3]   Planck residuals anomaly as a fingerprint of alternative scenarios to inflation [J].
Domenech, Guillem ;
Chen, Xingang ;
Kamionkowski, Marc ;
Loeb, Abraham .
JOURNAL OF COSMOLOGY AND ASTROPARTICLE PHYSICS, 2020, (10)
[4]   Deep Channel Learning for Large Intelligent Surfaces Aided mm-Wave Massive MIMO Systems [J].
Elbir, Ahmet M. ;
Papazafeiropoulos, Anastasios ;
Kourtessis, Pandelis ;
Chatzinotas, Symeon .
IEEE WIRELESS COMMUNICATIONS LETTERS, 2020, 9 (09) :1447-1451
[5]   Toward Smart Wireless Communications via Intelligent Reflecting Surfaces: A Contemporary Survey [J].
Gong, Shimin ;
Lu, Xiao ;
Hoang, Dinh Thai ;
Niyato, Dusit ;
Shu, Lei ;
Kim, Dong In ;
Liang, Ying-Chang .
IEEE COMMUNICATIONS SURVEYS AND TUTORIALS, 2020, 22 (04) :2283-2314
[6]  
Jensen TL, 2020, INT CONF ACOUST SPEE, P5000, DOI [10.1109/ICASSP40776.2020.9053695, 10.1109/icassp40776.2020.9053695]
[7]  
Kay S., 1993, Fundamentals of Statistical Signal Processing, V1
[8]  
Li S., 2021, ARXIV210103822
[9]  
Li S., 2020, ARXIV201013008
[10]  
Liu C., 2020, ARXIV200901423, P1