Abstract

Genetic algorithms utilize populations of individual hypotheses that converge over time to a single optimum, even within a multimodal domain. This paper examines methods that enable genetic algorithms to identify multiple optima within multimodal domains by maintaining population members within the niches defined by the multiple optima. A new mechanism, Dynamic Niche Sharing, is developed that is able to efficiently identify and search multiple niches (peaks) in a multimodal domain. Dynamic niche sharing is shown to perform better than two other methods for multiple optima identification, Standard Sharing and Deterministic Crowding. To further improve performance, mating restrictions are used to increase the likelihood of producing highly fit offspring. Two new mating restriction mechanisms, Dynamic Line Breeding and Dynamic Inbreeding, are introduced that utilize dynamic niche sharing to proportionately populate local optima in a multimodal domain. Experiments presented in this paper ...

Citations