An Improved Mutation Operator Which Can Improve the Performance of Genetic Algorithm

Abstract

An improved combined mutation operator (CM) is proposed for the problems of premature convergence and local optimization which often occur in genetic algorithm (GA). The CM operator combines the Gaussian mutation and the initial mutation to perform local initialization operations on individuals in the population, and maintain the population diversity while improving the local search ability of the operator. The results of 15 benchmark optimization problems show that the proposed CM operator can effectively improve the performance of the algorithm, and compared with other advanced algorithms, the improved algorithm (IRCGA) has stronger search capabilities and faster convergence speed.