Analysis of the Effect of Elite Count on the Behavior of Genetic Algorithms: A Perspective

Abstract

Various parameters affect the performance of Genetic Algorithms in terms of the accuracy of the optimal solution achieved and convergence rate. In this paper, effect of one such important parameter (elite count) on the behavior of Genetic Algorithms is meticulously analyzed, A standard benchmark function 'Rastrigin's Function' is used for the purpose of the study, and the results indicate that the extremely high values of elite count result in premature convergence on local minima, while low values of elite count result in much better solutions, near to the global optima.