Enhancing NOMA Handover Performance Using Hybrid AI-Driven Modulated Deterministic Sequences

TL;DR

This paper introduces a hybrid AI-driven method combining modulated sequences and deep reinforcement learning to significantly enhance NOMA handover performance, reducing interference and increasing success rates in 5G networks.

Contribution

It presents a novel hybrid approach that integrates Gold-Walsh sequences with Deep Q-Networks for dynamic interference management during NOMA handovers.

Findings

95.2% handover success rate achieved

Up to 28% throughput gain

Interference reduced by up to 41%

Abstract

Non-Orthogonal Multiple Access (NOMA) is an information-theoretical approach used in 5G networks to improve spectral efficiency, but it is prone to interference during handovers. In this work, we propose a hybrid method that combines Gold-Walsh modulated sequences with Deep Q-Networks (DQN) to intelligently manage interference during NOMA handovers. This method optimizes sequence selection and power allocation dynamically. As a result, it achieves a 95.2\% handover success rate, which is an improvement of up to 23.1 percentage points. It also delivers up to 28\% throughput gain and reduces interference by up to 41\% in various mobility scenarios. All improvements are statistically significant (\(p < 0.001\)). The DQN trains in \(4{,}200 \pm 400\) episodes with a complexity of \(O(N \log N + d \cdot h + \log B)\) and can be deployed in real-time.