Efficient swarm intelligent optimization techniques using cooperative spectrum sensing for terrestrial handovers

A cognitive radio network (CRN) is a dynamic and intelligent radio technology that optimizes spectral efficiency to enhance user experience in any terrestrial communication network. The cooperative spectrum sensing methods tend to significantly improve the sensing performance of cognitive radio to enable interference-free communication in a multi-user environment. Further, the cognition ability of cognitive radio, such as dynamic decision making and self-adaptation, is enhanced by applying Artificial Intelligent (AI) algorithms for learning and optimization. In this research, an AI-based cooperative prediction-based spectrum sensing (CPSS) model is considered to collect the prediction results of channel state information from parallel cognitive users. An evolutionary swarm-based learning model called SpecBFO (Spectrum-based Bacterial Foraging Optimization) algorithm is proposed to enable rapid spectrum decision making. The performance of the suggested SpecBFO model is evaluated to study the convergence probability and time complexity by analyzing the cost function. The experimental results confirms that the running time of the proposed work is optimal and achieves more accuracy compared to Genetic Algorithm (GA) by 80%, Particle Swarm Optimization (PSO) by 86.37%, and Bacterial Foraging Optimization (BFO) by 91.43% under minimum iteration at an SNR of − 15 dB.