Spectrum Sensing in Cognitive Radio Using Multiple Antenna by Eliminating Phase Noise

Efficient spectrum sensing is crucial in Cognitive Radio Networks (CRNs) to identify and utilize unoccupied frequency bands, unobtrusively for primary users. By providing spatial diversity, the use of multiple antennas can enhance spectrum sensing performance. The proposed work makes use of multiple antenna spectrum sensing with a Deep Q Network (DQN) model to ascertain the existence of an estimated signal. The presence of phase noise reduces the efficiency of spectrum sensing compared to other widely used methods. To overcome this, the proposed work adopts Jelly Fish Optimization (JFO), Single Candidate Optimization (SCO) and Sand cat swarm optimization algorithms with Multiple Antenna Spectrum Sensing DQN (MASSDQN) to decrease the phase noise and enhance the spectrum sensing. The experimental outcome demonstrates the superior performance of the sand cat swarm optimization technique in multiple antenna spectrum sensing and optimize the phase noise for the secondary users to harness the spectrum effectively.