GPU-Accelerated Machine Learning in Non-Orthogonal Multiple Access

TL;DR

This paper presents a GPU-accelerated neural network architecture that combines linear and non-linear processing for improved real-time detection in NOMA systems, demonstrating superior performance over traditional methods.

Contribution

It introduces a novel neural network design optimized for GPU implementation, enhancing real-time detection in NOMA networks with combined processing strategies.

Findings

GPU implementation achieves real-time detection

Superiority over conventional NOMA detection methods

Effective in laboratory measurement scenarios

Abstract

Non-orthogonal multiple access (NOMA) is an interesting technology that enables massive connectivity as required in future 5G and 6G networks. While purely linear processing already achieves good performance in NOMA systems, in certain scenarios, non-linear processing is mandatory to ensure acceptable performance. In this paper, we propose a neural network architecture that combines the advantages of both linear and non-linear processing. Its real-time detection performance is demonstrated by a highly efficient implementation on a graphics processing unit (GPU). Using real measurements in a laboratory environment, we show the superiority of our approach over conventional methods.