The contingent design for the optimal parameter settings of genetic algorithms
Chen‐Fang Tsai, Kuo‐Ming Chao · 2008
It is very difficult to accurately predict Genetic Algorithm evolutions and estimate the effects of any change in the operator and parameter settings. So, the setting of the parameter values is guesswork largely. This research applied the concept of Orthogonal Arrays as a tool for identifying the optimal operator and parameter settings for a Genetic Algorithm. This approach was based on the method of a robust experimental design which is attributed by the Taguchi method. The proposed method used Orthogonal Arrays to design a series of experiments which allow the calculation of the optimal value for each of the related variables. The Taguchi method has been applied with a fair degree of success in many practical experiments. This research utilized the theoretical experiment testbeds designed by DeJong’s for different search environments in order to improve the efficiency for genetic algorithm operations.