Exploiting Deep Learning in the Performance Evaluation of EH-Based Coordinated Direct and Relay Transmission System With Cognitive NOMA
Alok Kumar Shukla, Kajal Yadav, Prabhat K. Upadhyay, Jules M. Moualeu
Abstract
This letter investigates an energy harvesting (EH)-assisted coordinated direct and relay transmission in an overlay cognitive non-orthogonal multiple access (NOMA) system assuming perfect and imperfect successive interference cancellation. Specifically, we derive analytical expressions of the outage probability (OP) which include an infinite series, system throughput, and energy efficiency. Moreover, an asymptotic analysis of the OP in the high signal-to-noise ratio is carried out. Closed-form expressions of the exact OP and the ergodic sum capacity (ESC) are intractable owing to the complexity of the proposed scheme. To tackle this problem, we propose a deep learning (DL) framework to predict both the OP and ESC performances. The predicted results through the DL framework are shown to be consistent with the numerical results.