A Multi-objective Genetic Algorithm Based on Clustering
Wenbin Li, Guanqi Guo, Tanshan Yan · 2012
In order to further ease the disaster of computing costs in multi-objective optimization problem, we've put forward a kind of multi-objective genetic algorithm based on clustering. The algorithm uses the fuzzy c-means clustering control the similar individuals gathered in a class and for each class construct non-dominated set with arena's principle, so that we can use faster speed to choose the non-dominated individuals, then according to the distribution of each class, sampling structure new evolution sample and effectively ensure the diversity of population. Theoretical analysis and numerical experiment results show that the proposed algorithm has higher search performance, and the distribution and convergence are more ideal.