Genetic Algorithm With Species Differentiation Based on Kernel Support Vector Machine for Optimal Design of Wind Generator

In this paper, a novel genetic algorithm (GA) that employs species differentiation (SD) is proposed. The GA with SD (GA-SD) improves the convergence speed of the GA through the separation and progress of elite species that are classified by a kernel support vector machine. Furthermore, the GA-SD maintains exploration capability through the progress of inferior species and the gradual transition between species. To verify the effectiveness of the GA-SD, GA-SD was compared with the conventional GA on test functions. Finally, we applied the GA-SD for the optimal design of the wind generator.