Channelformer: Attention based Neural Solution for Wireless Channel Estimation and Effective Online Training

TL;DR

Channelformer is a neural network architecture employing attention mechanisms and pruning for efficient, accurate wireless channel estimation in OFDM systems, with an effective online training method suitable for 5G NR.

Contribution

The paper introduces Channelformer, a novel attention-based neural network with pruning and online training tailored for improved wireless channel estimation in 5G systems.

Findings

Achieves up to 70% parameter reduction with maintained performance.

Outperforms other neural network methods in channel estimation accuracy.

Demonstrates effective online training using receiver-only information.

Abstract

In this paper, we propose an encoder-decoder neural architecture (called Channelformer) to achieve improved channel estimation for orthogonal frequency-division multiplexing (OFDM) waveforms in downlink scenarios. The self-attention mechanism is employed to achieve input precoding for the input features before processing them in the decoder. In particular, we implement multi-head attention in the encoder and a residual convolutional neural architecture as the decoder, respectively. We also employ a customized weight-level pruning to slim the trained neural network with a fine-tuning process, which reduces the computational complexity significantly to realize a low complexity and low latency solution. This enables reductions of up to 70\% in the parameters, while maintaining an almost identical performance compared with the complete Channelformer. We also propose an effective online training method based on the fifth generation (5G) new radio (NR) configuration for the modern communication systems, which only needs the available information at the receiver for online training. Using industrial standard channel models, the simulations of attention-based solutions show superior estimation performance compared with other candidate neural network methods for channel estimation.