A diversified shuffled frog leaping: An application for parameter identification

This paper proposes a modified shuffled frog leaping (SFL) for solving parameter identification problems. The SFL divides a population into several memeplexes and then improves each memeplex in an evolutionary process. One of the main drawbacks of SFL is a limitation in its number and variety of search moves. This modification concentrates to diversify search moves of SFL by inserting a differential operator into evolutionary process of SFL. Experiments are performed on parameter identification problems and the obtained results are compared with some other algorithms reported in the literature. Practical experiences show that the proposed algorithm is very effective and robust so that it produces similar and promising results over repeated runs. The obtained results demonstrate a significantly better performance of our proposed algorithm than other revolutionary algorithms reported in the literature.