Optimization of Cognitive Radio System Using Self-Learning Salp Swarm Algorithm

Cognitive Radio (CR) has been developed as an enabling technology that allows the unused or underused spectrum to be used dynamically increase spectral efficiency. To improve overall performance of CR system it is extremely important adapt reconfigure parameters. The Decision Engine a major module in CR-based not only includes radio monitoring and cognition functions but also responsible for parameter adaptation. As meta-heuristic algorithms offer numerous advantages compared traditional mathematical approaches, these investigated order design efficient able transmitting parameters effectively reduce power consumption, bit error rate adjacent interference channel, while maximized secondary user throughput. Self-Learning Salp Swarm Algorithm (SLSSA) recent algorithm enhanced version SSA inspired by swarming behavior salps. In this work, parametric adaption performed SLSSA simulation results show high accuracy, stability outperforms other competitive maximizing throughput users. obtained with are shown satisfactory need fewer iterations converge methods.