A New Cat Swarm Optimization with Adaptive Parameter Control

摘要

Cat Swarm Optimization (CSO) is a new swarm intelligence based algorithm, which simulates the behaviors of cats. In CSO, there are two search modes including seeking and tracing. For each cat (solution) in the swarm, its search mode is determined by a parameter MR (mixture ratio). In this paper, we propose a new CSO algorithm by dynamically adjusting the parameter MR. In addition, a Cauchy mutation operator is utilized to enhance the global search ability. To verify the performance of the new approach, a set of twelve benchmark functions are tested. Experimental results show that the new algorithm performs better than the original CSO algorithm.