Solving Multi-modal Dynamic Optimization problems (MDO) has been a challenge for genetic algorithms (GAs). In this kind of optimization, an algorithm requires not only to find the multiple optimal solutions but also to locate a changing optimum dynamically. To enhance the performance of GAs in MDO, this paper proposes a New Genetic Operator NGO. The NGO is built on three components. First, a novel Genetic Algorithm with Dynamic Niche Sharing (GADNS) which permits to encourage the speciation. Second, an unsupervised fuzzy clustering that tracks multiple optima and enhances GADNS. Third, Spacial Separation (SS) which induces the stable sub-populations and allows local competition. In addition, NGO maintains diversity by a new genetic operators. To control the selection pressure, a new tournament selection is presented. Moving Peaks benchmark is applied to test the performance of NGO. The ability of the NGO to track multiple optima is demonstrated by a new diversity measure. © 2013 Springer Science+Business Media Dordrecht.
CITATION STYLE
Jebari, K., Bouroumi, A., & Ettouhami, A. (2013). Fertilization operator for multi-modal dynamic optimization. In Lecture Notes in Electrical Engineering (Vol. 229 LNEE, pp. 475–489). Springer Verlag. https://doi.org/10.1007/978-94-007-6190-2_36
Mendeley helps you to discover research relevant for your work.