A Weighted Autoencoder-Based Approach to Downlink NOMA Constellation Design

TL;DR

This paper introduces a weighted autoencoder framework for designing downlink NOMA constellations, enabling flexible error probability control for multiple users without explicit channel quality information, leading to improved performance.

Contribution

It proposes a novel weighted loss function in autoencoder training for NOMA, enhancing multi-user constellation design and error probability management.

Findings

Significant improvement in achievable error levels.

Flexible control of user error probabilities.

Enhanced performance with SICNet decoder.

Abstract

End-to-end design of communication systems using deep autoencoders (AEs) is gaining attention due to its flexibility and excellent performance. Besides single-user transmission, AE-based design is recently explored in multi-user setup, e.g., for designing constellations for non-orthogonal multiple access (NOMA). In this paper, we further advance the design of AE-based downlink NOMA by introducing weighted loss function in the AE training. By changing the weight coefficients, one can flexibly tune the constellation design to balance error probability of different users, without relying on explicit information about their channel quality. Combined with the SICNet decoder, we demonstrate a significant improvement in achievable levels and flexible control of error probability of different users using the proposed weighted AE-based framework.