A Study on Six Memetic Strategies for Multimodal Optimisation by Differential Evolution

This paper presents an experimental study on memetic strategies to enhance the performance of population-based metaheuristics for multimodal optimisation. The purpose of this work is to devise some recommendations about algorithmic design to allow a successful combination of local search and niching techniques. Six memetic strategies are presented and tested over five population-based algorithms endowed with niching techniques. Experimental results clearly show that local search enhances the performance of the framework for multimodal optimisation in terms of both peak ratio and success rate. The most promising results are obtained by the variants that employ an archive that pre-selects the solutions undergoing local search thus avoiding computational waste. Furthermore, promising results are obtained by variants that reduce the exploitation pressure of the population-based framework by using a simulated annealing logic in the selection process, leaving the exploitation task to the local search.