Evaluation of novel adaptive evolutionary programming on four constraint handling techniques

Abstract

This paper presents empirical studies carried out to evaluate the performance of different constraint handling methods on constrained real-parameter optimization using a novel adaptive evolutionary programming (EP). 25 runs have been conducted for each of the 13 test problems considered. Our experimental results show that no single constraint handling method can be the best for all problems i.e, each constraint handling method is suitable only for a subset of problems. We also show that the novel adaptive EP proposed in this paper has improved performance over the classical EP (CEP).