ANALYZE AND EVALUATE THE PERFORMANCE OF NOMA-CRN USING DEEP LEARNING

Abstract

The performance of Non-Orthogonal Multiple Access Cognitive Radio Network (NOMA-CRN) for two users is analyzed and evaluated using deep learning in this paper. To this end, we firstly recommend an exact closed-form outage probability formula for NOMA[1]CRN. Next, we conduct Monte-Carlo simulations to corroborate the recommended formula. Moreover, deep learning is applied to evaluate the exactness of the estimated outage probability as compared to theory and simulation. Finally, we provide multiple results to demonstrate the influence of crucial specifications on the performance of NOMA-CRN.