On memetic Differential Evolution frameworks: A study of advantages and limitations in hybridization

This paper aims to study the benefits and limitations in the hybridization of the differential evolution with local search algorithms. In order to perform this study, the performance of three memetic algorithms employing a differential evolution as an evolutionary framework and several local search algorithms adaptively coordinated by means of a fitness diversity logic have been analyzed. The performance of a standard differential evolution whose parameter setting has been executed only after fine tuning has also been taken into account in the comparison. The comparative analysis has been performed on a set of various test functions. Numerical results show that the memetic algorithms without any extensive parameter tuning are still competitive with the finely tuned plain differential evolution.