Parallel and distributed evolutionary computations for multimodal function optimization

Abstract

A number of evolutionary computations (ECs) have been developed for solving multimodal function optimization problems (MFOPs). Some of the well-known ones are: fitness sharing, sequential niching, simple subpopulation schemes and co-evolutionary shared niching. These ECs have shown the capability of solving MFOPs, but have introduced one or more parameters that cannot be easily set without prior knowledge of the fitness landscape. Moreover, a priori knowledge of a particular MFOP may not always be readily available. In this work, we describe a set of parallel and distributed ECs that are capable of locating all the peaks in a MFOP without using parameters that require specific topological information. This paper also provides a performance comparison between three approaches to solving MFOPs: fitness sharing, parallel EC and distributed EC.