A Reachability-Distance Based Differential Evolution With Individual Transfer for Multimodal Optimization Problems

Multimodal optimization problems (MMOPs) are one of the most challenging optimization problems in the real world, which need to locate multiple global optima with high accuracy, simultaneously. Although many niching techniques, such as crowding and species have been widely used for solving MMOPs, how to reduce the influence of introduced niching parameters and how to deal with the individuals trapped into local optima are still challenges for the existing multimodal algorithms. In this paper, a novel reachability-distance based differential evolution with individual transfer (RDDE-IT) is proposed to better deal with MMOPs, which includes the following three contributions. Firstly, a reachability-distance based prim (RDP) niching strategy without sensitive parameters is proposed to divide the population, which can adaptively adjust the number of niches as evolution progress. Secondly, an individual state-based mutation (ISM) strategy is proposed to help each individual select a suitable mutation operator. Thirdly, an adaptive individual transfer (AIT) strategy is proposed to deal with the individuals trapped into local optima and determines the probability of new individuals being generated within each niche. The performance of RDDE-IT is compared with 13 state-of-the-art algorithms on CEC'2013 and the experimental results show that RDDE-IT achieves significant advantages on high-dimension problems.