Effects of Population Size and Mutation Rate on Results of Genetic Algorithm

Abstract

The study of genetics algorithms (GAs) with finite population size requires the stochastic treatment of evolution. In this study, we examined effects of genetic fluctuations on the performance of GA calculations. We considered the roles of mutation by using the stochastic schema theory within the framework of the Wright-Fisher model of Markov processes. The success probability of obtaining the optimum solution was investigated experimentally and theoretically. We noticed that mutation has effects of increasing the success probabilities. We also noticed crossover brings the population a good effect in results of GA.