Performance Analysis on Machine Learning-Based Channel Estimation

Recently, machine learning-based channel estimation has attracted much attention. The performance of machine learning-based estimation has been validated by simulation experiments. However, little attention has been paid to the theoretical performance analysis. In this paper, we investigate the mean square error (MSE) performance of machine learning-based estimation. Hypothesis testing is employed to analyze its MSE upper bound. Furthermore, we build a statistical model for hypothesis testing, which holds when the linear learning module with a low input dimension is used in machine learning-based channel estimation, and derive a clear analytical relation between the size of the training data and performance. Then, we simulate the machine learning-based channel estimation in orthogonal frequency division multiplexing (OFDM) systems to verify our analysis results. Finally, the design considerations for the situation where only limited training data is available are discussed. In this situation, our analysis results can be applied to assess the performance and support the design of machine learning-based channel estimation.

[1]  张玲,et al.  MIMO Channel Estimation and Equalization Using Three-Layer Neural Networks with Feedback , 2007 .

[2]  Theodore S. Rappaport,et al.  3-D Millimeter-Wave Statistical Channel Model for 5G Wireless System Design , 2016, IEEE Transactions on Microwave Theory and Techniques.

[3]  Geoffrey Ye Li,et al.  MIMO-OFDM for wireless communications: signal detection with enhanced channel estimation , 2002, IEEE Trans. Commun..

[4]  Xiaoli Ma,et al.  Deep Learning-Based Channel Estimation for Doubly Selective Fading Channels , 2019, IEEE Access.

[5]  Stephen E. Fienberg,et al.  Testing Statistical Hypotheses , 2005 .

[6]  Xiaochen Zhang,et al.  Online Extreme Learning Machine-Based Channel Estimation and Equalization for OFDM Systems , 2019, IEEE Communications Letters.

[7]  V. K. Jones,et al.  Channel estimation for wireless OFDM systems , 1998, IEEE GLOBECOM 1998 (Cat. NO. 98CH36250).

[8]  Wolfgang Utschick,et al.  Learning the MMSE Channel Estimator , 2017, IEEE Transactions on Signal Processing.

[9]  Jeffrey G. Andrews,et al.  One-Bit OFDM Receivers via Deep Learning , 2018, IEEE Transactions on Communications.

[10]  Himanshu Sharma,et al.  Channel Estimation in OFDM Systems , 2013 .

[11]  Robert W. Heath,et al.  Channel Estimation and Hybrid Precoding for Millimeter Wave Cellular Systems , 2014, IEEE Journal of Selected Topics in Signal Processing.

[12]  Masoud Ardakani,et al.  Decision Directed Channel Estimation Based on Deep Neural Network $k$ -Step Predictor for MIMO Communications in 5G , 2019, IEEE Journal on Selected Areas in Communications.

[13]  Geoffrey Ye Li,et al.  Deep Learning-Based Channel Estimation for Beamspace mmWave Massive MIMO Systems , 2018, IEEE Wireless Communications Letters.

[14]  Daesik Hong,et al.  Performance analysis of channel estimation for OFDM systems with residual timing offset , 2006, IEEE Transactions on Wireless Communications.

[15]  Steven Kay,et al.  Fundamentals Of Statistical Signal Processing , 2001 .

[16]  Richard F. Gunst,et al.  Applied Regression Analysis , 1999, Technometrics.

[17]  Emil Björnson,et al.  Channel Estimation in Massive MIMO Under Hardware Non-Linearities: Bayesian Methods Versus Deep Learning , 2020, IEEE Open Journal of the Communications Society.

[18]  Jian Song,et al.  Deep Learning-Based Channel Estimation Algorithm Over Time Selective Fading Channels , 2019, IEEE Transactions on Cognitive Communications and Networking.

[19]  Yu Zhang,et al.  Deep Learning for Massive MIMO With 1-Bit ADCs: When More Antennas Need Fewer Pilots , 2020, IEEE Wireless Communications Letters.

[20]  Ahmed Alkhateeb,et al.  Deep Learning for TDD and FDD Massive MIMO: Mapping Channels in Space and Frequency , 2019, 2019 53rd Asilomar Conference on Signals, Systems, and Computers.

[21]  Xiaobo Zhou,et al.  Channel estimation for OFDM systems using adaptive radial basis function networks , 2003, IEEE Trans. Veh. Technol..

[22]  Aymen Omri,et al.  CHANNEL ESTIMATION FOR LTE UPLINK SYSTEM BY PERCEPTRON NEURAL NETWORK , 2010 .

[23]  Jae-Mo Kang,et al.  Deep-Learning-Based Channel Estimation for Wireless Energy Transfer , 2018, IEEE Communications Letters.

[24]  Hamid Sheikhzadeh,et al.  Deep Learning-Based Channel Estimation , 2018, IEEE Communications Letters.

[25]  Seung Young Park,et al.  Performance of pilot-assisted channel estimation for OFDM system under time-varying multi-path Rayleigh fading with frequency offset compensation , 2000, VTC2000-Spring. 2000 IEEE 51st Vehicular Technology Conference Proceedings (Cat. No.00CH37026).

[26]  Yves Louët,et al.  LMMSE channel estimation in OFDM context: a review , 2017, IET Signal Process..

[27]  Per Ola Börjesson,et al.  OFDM channel estimation by singular value decomposition , 1996, Proceedings of Vehicular Technology Conference - VTC.

[28]  Yunlong Cai,et al.  Deep Learning Based Channel Estimation Algorithm for Fast Time-Varying MIMO-OFDM Systems , 2020, IEEE Communications Letters.

[29]  Geoffrey Ye Li,et al.  Robust channel estimation for OFDM systems with rapid dispersive fading channels , 1998, IEEE Trans. Commun..