摘要
Surrogate models have shown to be effective in assisting evolutionary algorithms(EAs)for solving computationally expensive complex optimization problems.However,the effectiveness of the existing surrogate-assisted evolutionary algorithms still needs to be improved.A data-driven evolutionary sampling optimization(DESO)framework is proposed,where at each generation it randomly employs one of two evolutionary sampling strategies,surrogate screening and surrogate local search based on historical data,to effectively balance global and local search.In DESO,the radial basis function(RBF)is used as the surrogate model in the sampling strategy,and different degrees of the evolutionary process are used to sample candidate points.The sampled points by sampling strategies are evaluated,and then added into the database for the updating surrogate model and population in the next sampling.To get the insight of DESO,extensive experiments and analysis of DESO have been performed.The proposed algorithm presents superior computational efficiency and robustness compared with five state-of-the-art algorithms on benchmark problems from 20 to 200 dimensions.Besides,DESO is applied to an airfoil design problem to show its effectiveness.
基金
supported by the National Natural Science Foundation of China(62076225,62073300)
the Natural Science Foundation for Distinguished Young Scholars of Hubei(2019CFA081)
the Fundamental Research Funds for the Central Universities,China University of Geosciences(Wuhan)(CUGGC03).
作者简介
ZHEN Huixiang was born in 1995.He is now pursuing his Ph.D.degree in the School of Computer Science,China University of Geosciences,Wuhan,China.His research interests include the evolutionary computation and its applications.E-mail:zhenhuixiang@cug.edu.cn;Corresponding author:GONG Wenyin was born in 1979.He is currently a professor and Ph.D.student supervisor in the School of Computer Science,China University of Geosciences,Wuhan,China.He has published over 50 research papers in journals and international conferences.His research interests include differential evolution,memetic algorithms,multi-objective optimization,and their applications.E-mail:wygong@cug.edu.cn;WANG Ling was born in 1972.He is currently a professor and Ph.D.student supervisor in the Department of Automation,Tsinghua University,Beijing,China.He has authored five academic books and over 260 refereed papers.His research interests include intelligent optimization and production scheduling.E-mail:wangling@tsinghua.edu.cn。
