Spectrum Sensing and Management using Orthogonal Frequency Division Multiplexing based on Cognitive Radio Networks with Cooperative Spectrum Sensing

Nowadays, the fixed spectrum assignment policy restricts the availability of radio spectrum resources, hindering the growth of wireless applications, leading to spectrum scarcity, inefficiencies, and limitations on innovation. This is utilized by constraining full potential of wireless technologies and their associated benefits. However, the sensing system lacks in High computational complexity and energy consumption in spectrum sensing that leads to delays and inefficiencies in cognitive radio networks, limiting real-time adaptability and hindering seamless communication, which can compromise network performance and reliability. To overcome these drawbacks, a classification method is proposed using Orthogonal Frequency Division Multiplexing Based on The Cognitive Radio Networks with Cooperative Spectrum Sensing (OFDM based on CRN-CSS). Initially data is collected from RadioML2016 dataset, then the preprocessing is performed by the scarred convolution, random demodulator, random filtering and then compressive multiplexer. Then the features are selected using optimization method Ant Colony Optimization (ACO). Finally, the classification is performed using OFDM based on CRN-CSS whereas it enhances the adaptability to dynamic spectrum environments. The results prove that the model show better performance in terms of accuracy, precision and F1 score when compared to previous existing method of Particle Swarm Optimization (PSO).