Learning The MMSE Channel Predictor

TL;DR

This paper introduces a neural network-based channel predictor that improves upon traditional LMMSE methods by leveraging assumptions about the channel model, leading to better prediction accuracy in wireless communication systems.

Contribution

The paper develops a neural network predictor initialized from a weighted sum of LMMSE predictors, outperforming classical methods under specific channel assumptions.

Findings

Neural network predictor outperforms LMMSE predictor under Jakes Doppler spectrum assumptions.

The proposed method effectively leverages assumptions to improve channel prediction accuracy.

Initialization from weighted LMMSE predictors aids neural network training and performance.

Abstract

We present a neural network based predictor which is derived by starting from the linear minimum mean squared error (LMMSE) predictor and by further making two key assumptions. With these assumptions, we first derive 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 under the given channel model assumptions it is possible to easily outperform the LMMSE predictor based on the Jakes assumption of the underlying Doppler spectrum.