An Empirical Performance Analysis of Differential Evolution Variants on Unconstrained Global Optimization Problems

Abstract

In this paper we present an empirical, comparative performance, analysis of fourteen Differential Evolution (DE) variants on different classes of unconstrained global optimization benchmark problems. This analysis has been undertaken, with an objective, to compare and to identify competitive DE variants which perform reasonably well on problems with different features. Towards this, fourteen variants of DE are benchmarked on 14 high dimensional unconstrained test functions grouped by their modality and decomposability viz. unimodal separable, unimodal nonseparable, multimodal separable and multimodal nonseparable. The analysis identifies the overall competitive variants as well as the feature based performances of all the variants.