Reproducible Evaluation of Neural Network Based Channel Estimators And Predictors Using A Generic Dataset

A low-complexity neural network based approach for channel estimation was proposed recently, where assumptions on the channel model were incorporated into the design procedure of the estimator. Instead of using data from a measurement campaign as done in previous work, we evaluate the performance of the convolutional neural network (CNN) based channel estimator by using a reproducible mmWave environment of the DeepMIMO dataset. We further propose a neural network based predictor which is derived by starting from the linear minimum mean squared error (LMMSE) predictor. We start by deriving a weighted sum of LMMSE predictors which is motivated by the structure of the optimal MMSE predictor. This predictor provides an initialization (weight matrices, biases and activation function) to a feed-forward neural network based predictor. With a properly learned neural network, we show that it is possible to easily outperform the LMMSE predictor based on the Jakes assumption of the underlying Doppler spectrum in an reproducible indoor scenario of the DeepMIMO dataset.

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

[2]  Y. C. Pati,et al.  Orthogonal matching pursuit: recursive function approximation with applications to wavelet decomposition , 1993, Proceedings of 27th Asilomar Conference on Signals, Systems and Computers.

[3]  Christoph F. Mecklenbräuker,et al.  Time-Variant Channel Prediction using Time-Concentrated and Band-Limited Sequences , 2006, 2006 IEEE International Conference on Communications.

[4]  Ahmed Alkhateeb,et al.  DeepMIMO: A Generic Deep Learning Dataset for Millimeter Wave and Massive MIMO Applications , 2019, ArXiv.

[5]  R. Clarke A statistical theory of mobile-radio reception , 1968 .

[6]  Wolfgang Utschick,et al.  Learning-Based Channel Estimation for Various Antenna Array Configurations , 2019, 2019 IEEE 20th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC).

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

[8]  Wolfgang Utschick,et al.  Low-Complexity Computation of LMMSE Channel Estimates in Massive MIMO , 2015, WSA.

[9]  Christoph F. Mecklenbräuker,et al.  Minimum-Energy Band-Limited Predictor With Dynamic Subspace Selection for Time-Variant Flat-Fading Channels , 2007, IEEE Transactions on Signal Processing.

[10]  Abbas Jamalipour,et al.  Wireless communications , 2005, GLOBECOM '05. IEEE Global Telecommunications Conference, 2005..

[11]  Robert M. Gray,et al.  Toeplitz and Circulant Matrices: A Review , 2005, Found. Trends Commun. Inf. Theory.

[12]  Ronald N. Bracewell,et al.  The Fourier Transform and Its Applications , 1966 .

[13]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[14]  Wolfgang Utschick,et al.  Learning the MMSE Channel Predictor , 2019, 2020 IEEE International Conference on Communications Workshops (ICC Workshops).

[15]  Wolfgang Utschick,et al.  Evaluation of Neural-Network-Based Channel Estimators Using Measurement Data , 2019, WSA.