Meta optimized hybrid beamforming and adaptive clustering for SNR Aware LIS aided mmWave MIMO NOMA networks

Next-generation wireless networks demand high spectral and energy efficiency to support massive connectivity, especially in dense urban and IoT-centric environments. Millimeter-wave (mmWave) MIMO-NOMA systems, when combined with large intelligent surfaces (LIS), offer a promising pathway, but existing methods often struggle with static clustering, suboptimal beamforming, and limited adaptability to real-time SNR fluctuations. Traditional algorithms such as GA and PSO fail to deliver robust performance in dynamic user scenarios due to rigid optimization and insufficient coordination between beamforming and user clustering. To overcome these limitations, this research introduces a meta-optimized hybrid beamforming and adaptive clustering framework for SNR-aware LIS-aided mmWave MIMO-NOMA systems. The proposed approach integrates a dual-stage optimization strategy using a Modified Seagull Optimization Algorithm (MSOA). In the first stage, MSOA dynamically optimizes hybrid analog–digital beamforming to align with mmWave channel characteristics. In the second stage, adaptive clustering groups the users based on SNR, spatial correlation, and distance, thereby enhancing NOMA efficiency and user fairness. Implemented on Python with NYUSIM-based mmWave channel modeling, the system is tested under realistic LIS-aided conditions. Comparative simulations show that the proposed method achieves a sum-rate of 56.8 bps/Hz, Jain’s Fairness Index of 0.91, and energy efficiency improvement over 15% compared to GA, PSO, K-Medoids, and FCM-based schemes. Moreover, outage probability significantly drops to 8 × 10⁻⁴ at 30 dB SNR, confirming the system’s robustness. By enabling intelligent beam-cluster alignment and smarter resource usage, this method addresses major scalability and efficiency gaps, offering a practical and high-performing solution for 6G wireless systems. The proposed framework sets a strong foundation for future enhancements in adaptive communication systems.