Learning Short Codes for Fading Channels with No or Receiver-Only Channel State Information

TL;DR

This paper introduces a deep learning-based autoencoder approach to design short-length codes for fading channels with no or receiver-only channel state information, outperforming classical codes in these scenarios.

Contribution

It proposes a novel autoencoder architecture for designing short codes tailored to fading channels with limited or no CSI, demonstrating improved performance over classical codes.

Findings

Learned codes are mutually orthogonal with full support of the fading distribution.

Codes are not mutually orthogonal when the support is limited to non-negative real line.

Deep learning-designed codes outperform classical codes in fading channels with CSI constraints.

Abstract

In next-generation wireless networks, low latency often necessitates short-length codewords that either do not use channel state information (CSI) or rely solely on CSI at the receiver (CSIR). Gaussian codes that achieve capacity for AWGN channels may be unsuitable for these no-CSI and CSIR-only cases. In this work, we design short-length codewords for these cases using an autoencoder architecture. From the designed codes, we observe the following: In the no-CSI case, the learned codes are mutually orthogonal when the distribution of the real and imaginary parts of the fading random variable has support over the entire real line. However, when the support is limited to the non-negative real line, the codes are not mutually orthogonal. For the CSIR-only case, deep learning-based codes designed for AWGN channels perform worse in fading channels with optimal coherent detection compared to codes specifically designed for fading channels with CSIR, where the autoencoder jointly learns encoding, coherent combining, and decoding. In both no-CSI and CSIR-only cases, the codes perform at least as well as or better than classical codes of the same block length.