Real-Coded Genetic Algorithm Realizing Fast Convergence by Reducing Its Population Size

Abstract

Just generation gap (JGG) is a generational alternation model of real-coded genetic algorithms (GAs), and is excellent at finding the global optimum solution of a function optimization problem. However, its population size is large, and therefore its convergence speed is low. A method to accelerate the convergence speed is to reduce the population size. However, if it is reduced throughout the search by JGG, the population diversity is lost, which may cause the failure to find the global optimum solution. The population size should be reduced during only a part of the search period during which the population diversity is not lost. In this paper, we propose a real-coded GA realizing fast convergence by introducing the reduction of the population size into JGG. In the proposed method, the population size is reduced during only an early or late search period. The performance of the proposed method is empirically evaluated by comparing it with only JGG and an existing GA.