Improving the Search Efficiency of Differential Evolution Algorithm by Population Diversity Analysis and Adaptation of Mutation Step Sizes

Abstract

The aim of this research work is to improve the efficiency of differential evolution (DE) algorithm, at the cases of its unsuccessful searches. Initially, this work discusses and compares different methods to measure the population diversity of DE algorithm implemented for DE/rand/1/bin variant for a set of benchmarking functions. A method which well demonstrates difference in population diversity evolution at successful and unsuccessful cases of DE search is identified based on comparison. This work is then extended to detect unsuccessful searches in advance using the evolution of population diversity measured by the identified method. On detecting a search as unsuccessful, a parameter adaptation strategy to adapt the mutation step size (F) is added to DE algorithm to recover from it. The improved DE algorithm, which comprises of the logic of adapting F value based on the population diversity, is compared with its classical version and found outperforming. The comparison results are reported in this paper.