Optimizing Nonlinear Distortion and Interference in MC-CDMA Receivers Employing Deep Neural Networks

Abstract

Systems that employ multicarrier code division multiple access, commonly known as MC-CDMA, produce outstanding results in terms of both the performance of the system as a whole and the efficiency with which it uses the spectrum. However, multiple access strategies are susceptible to interference despite their high spectrum efficiency. This work aims to reduce multiple access interference (MAI) by developing an MC-CDMA receiver. When MC-CDMA deteriorates nonlinearly, standard receivers, namely, zero forcing (ZF), maximal ratio combining (MRC), minimum mean square error (MMSE), and equal gain combining (EGC), are unable to cancel MAI. Neural network (NN) receivers are a better option due to their nonlinear nature. Based on the simulation results, the suggested deep neural network- (DNN-)based schemes outperform the current baselines in terms of error handling and usability. This research explores the viability and effectiveness of a DNN-based receiver designed for MC-CDMA with nonlinearity degradations. The focus of this research is on MC-CDMA.