Performance Evaluation of ML-Based Classifiers for IRS-Aided NOMA-Based 6G Cognitive Radio Networks

Non-orthogonal multiple access (NOMA) is a notable technology for enhancing spectrum usage in wireless communication. On the other hand, cognitive radio (CR) networks are also renowned technology for increasing spectrum efficiency. However, fifth-generation wireless networks cannot provide a dynamic wireless environment. This barrier is overcome by sixth-generation (6G) wireless networks. In 6G, a dynamic wireless environment can be achieved by an intelligent reflecting surface (IRS). IRS is an eminent technology that enhances the overall quality of experience in wireless systems. This paper presents users’ performance analysis in IRS-aided NOMA-based 6G CR networks to capitalize on these technologies. The most popular five machine learning (ML)-based classifiers have been considered to sense the feature of the spectrum and evaluate the performance of the IRS-aided NOMA-based 6G CR network for the probability of detection, throughput, and energy efficiency. The simulation results have been validated for the proposed network with and without ML-based classifiers. Further, the performance of the proposed network has been tested for the different ratios of sensing time to total time, probability of false alarms, and different signal sizes of the CR network. The time complexity of the proposed network has been evaluated and found that the network has satisfactory inference time. The simulation results also suggest that the proposed network may fulfill the spectrum, energy, and reliability requirements of the 6G wireless networks.