Attention Based Neural Networks for Wireless Channel Estimation

TL;DR

This paper introduces a novel attention-based neural network architecture, HA02, utilizing transformer and residual networks to enhance wireless channel estimation in OFDM systems, demonstrating superior performance over existing methods.

Contribution

The paper presents the first hybrid encoder-decoder model using self-attention for wireless channel estimation, combining transformer and residual neural networks.

Findings

Superior estimation accuracy with 3GPP channel models

Effective focus on important input features via attention mechanism

Outperforms other neural network methods in simulations

Abstract

In this paper, we deploy the self-attention mechanism to achieve improved channel estimation for orthogonal frequency-division multiplexing waveforms in the downlink. Specifically, we propose a new hybrid encoder-decoder structure (called HA02) for the first time which exploits the attention mechanism to focus on the most important input information. In particular, we implement a transformer encoder block as the encoder to achieve the sparsity in the input features and a residual neural network as the decoder respectively, inspired by the success of the attention mechanism. Using 3GPP channel models, our simulations show superior estimation performance compared with other candidate neural network methods for channel estimation.