A failure remember-driven differential evolution
Xinchao Zhao, Dongyue Liu, Huiping Liu, Wenbo Ai · 2016
Differential evolution (DE) is one of the most efficient and powerful algorithms for global optimization problems and exhibits remarkable performance in scientific and engineering fields. In the past few years, various improved variants have been studied by many researchers. However, the neighborhood and direction information is not completely utilized in exploration and exploitation stages. In this paper, a failure remember-driven self-adaptive differential evolution algorithm, ATBDE, is proposed, which uses “Top-Bottom” strategy with optional archive and a parameter self-adapting strategy driven by “Failure Remember” operation. Experimental comparisons indicate that ATBDE has a competitive performance when comparing with other DE algorithms.