A Deep-SIC Channel Estimator Scheme in NOMA Network

Abstract

In 5G and next-generation mobile networks, reliable handover is a key requirement that ensures connection continuity, especially for mobile users and in high-density scenarios. However, conventional handover triggers based on instantaneous channel measurements are prone to failures and the ping-pong effect due to outdated or inaccurate channel state information. To address this, we propose Deep Successive Interference Cancellation (Deep-SIC), a knowledge-based channel prediction model that employs a Transformer-based approach to estimate channel quality and optimise handover decisions. Deep-SIC utilises Partially Decoded Data (PDD), a byproduct of SIC in Non-Orthogonal Multiple Access (NOMA), as a feedback signal to continually improve its predictions. This mechanism enables the model to learn quickly and stabilise their learning. Our model learns faster than existing state-of-the-art algorithms under the evaluated conditions, such as Graph-NOMA, while providing verifiable stability and resilience to user mobility (Theorem 2). The system-level simulation can substantially enhance network performance by mitigating the ping-pong effect and reducing the handover failure (HOF) rate, especially at vehicular speeds (e.g., 60 km/h). Moreover, Deep-SIC has a smaller normalised root mean square error (NRMSE) in low-SNR situations than state-of-the-art algorithms with linear computational complexity, O(K).