Deep Learning-Based Spectrum Sensing for TV White Space in 5G-MBMS Networks

Abstract

Accurate spectrum sensing in TV White Space (TVWS) is crucial for enhancing spectral efficiency in 5G Multimedia Broadcast Multicast Services (MBMS) networks. Traditional spectrum sensing techniques suffer from poor performance in low-SNR environments, necessitating a robust, data-driven approach. This study introduces a deep learning-based multi-feature fusion approach that integrates energy detection, cyclostationary analysis, and covariance matrix detection. The proposed model employs an adaptive thresholding mechanism and multi-task learning to enhance detection accuracy while ensuring real-time feasibility in dynamic spectrum environments. Our model implements multi-task learning for concurrent primary user detection and MBMS signal classification, featuring adaptive thresholds that adjust to signal conditions. Develops a novel multi-task learning-based spectrum sensing framework for concurrent primary user detection and MBMS signal classification. Introduces adaptive thresholding mechanisms to improve detection robustness under varying SNR conditions. Achieves 99% classification accuracy at −10 dB SNR, significantly outperforming traditional methods. Demonstrates practical feasibility for real-time spectrum sensing in 5G-MBMS networks.