A Comparative Study of Steady State and Generational Genetic Algorithms for Use in Nonstationary Environments

. The objective of this study is a comparison of two models of a genetic algorithm - the generational and incremental/steady state genetic algorithms - for use in the nonstationary/dynamic environments. It is experimentally shown that selection of a suitable version of the genetic algorithm can improve performance of the genetic algorithm in such environments.This can extend ability of the genetic algorithm to track the environmental changes which are relatively small and occur with a low frequency without need to implement an additional technique for tracking changing optima. 1 Introduction The genetic algorithm is a proven search/optimisation technique [Holland 1975] based on an adaptive mechanism of the biological systems. In our previous work we showed that the genetic algorithm is a suitable on-line optimization method to balance the load of the presses in a sugar beet pressing station [Fogarty,Vavak,Cheng 1995] and to balance the fuel load in a multiple burner boiler [Vavak,Foga..