Multi-Objective Modified Glowworm Swarm Optimization Algorithm for Efficient Spectrum Sensing in the Cognitive Radio Network

The combination of machine learning and Cognitive Radio (CR) technology has generated a lot of interest in research, especially in the field of spectrum management. Even with the possible advantages, high spectral efficiency, low latency, high network efficiency, and enhanced energy economy are only a few of the performance qualities that need to be addressed in order to prepare technology for spectrum management. But accomplishing these goals might frequently provide opposite difficulties. In the context of spectrum management, a new Multi-Objective Modified Glowworm Swarm Optimization (MOMGSO) approach is developed to handle multi-objective optimization issues. In order to achieve global optima, the Glowworm Swarm Optimization (GSO) modification seeks to achieve a balance between the exploration and exploitation processes. This tweak modifies the mutation coefficient, leader selection, and discrimination weight. An analysis is conducted between the suggested technique and current methods in terms of energy efficiency, interference, and throughput. The results of the simulation show that the MOMGWO algorithm outperforms existing techniques in terms of the Pareto front quality.