A Differential Evolution algorithm based on Ordering of individuals

Abstract

Differential Evolution (DE) algorithm has been shown to be powerful for many real optimization problems. To improve the robustness and convergence speed, we propose a novel method, which is ordering of individuals in the population. This has changed the structure of population in traditional DE algorithm, which is always randomly generated and randomly evolved. Ordering of individuals improved the stability of the evolved solution immensely. Differential Evolution algorithm based on Ordering of individuals (ODE) is the basic pattern of the applications of ordering and combined with other means, ordering would get a better performance to strengthen the robustness of DE algorithm. By the experimental testing of benchmark functions, the results show ODE algorithm has a better performance than DE algorithm especially in robustness.