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

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 $\mathrm{4,200}\pm 400$ episodes with a complexity of $O(N\log N+d\cdot h+\log B)$ and can be deployed in real-time.