Ergodic capacity estimation with artificial neural networks in noma-based cognitive radio systems

Abstract

The aim of this study is to predict the total ergodic capacity of near users in a cognitive radio (CR)-based non-orthogonal multiple access (NOMA) system model using the proposed artificial neural network (ANN) architecture. The input dataset used in this study was collected from the CR-NOMA system model and consists of the path loss coefficient, power allocation coefficient, signal-to-noise ratio, the distance between the source-relay-destination, and the ratio of the power of the secondary user to that of the primary user. Using a supervised learning method, the output data are trained and input into the ANN to estimate the ergodic capacity of nearby users using test data. The trained system model demonstrates an accuracy of 96.43% for training data, 96.34% for validation data, and 95.66% for test data when estimating the total ergodic capacity.