An efficient differential evolution algorithm based on orthogonal learning and elites local search mechanisms for numerical optimization
作者：
Highlights：
• Stagnation and premature convergence are distinguished by population diversity.
• Enhanced orthogonal learning scheme is proposed to recover population vitality.
• Elites local search method is designed to assist the orthogonal learning scheme.
• Algorithm design is based on the balance between exploration and exploitation.
• Experiments show that the proposed algorithm has superior performance.
摘要
•Stagnation and premature convergence are distinguished by population diversity.•Enhanced orthogonal learning scheme is proposed to recover population vitality.•Elites local search method is designed to assist the orthogonal learning scheme.•Algorithm design is based on the balance between exploration and exploitation.•Experiments show that the proposed algorithm has superior performance.
论文关键词：Differential evolution,Population stagnation,Premature convergence,Orthogonal learning,Local search,Numerical optimization
论文评审过程：Received 25 July 2021, Revised 18 September 2021, Accepted 21 October 2021, Available online 25 October 2021, Version of Record 1 November 2021.
论文官网地址：https://doi.org/10.1016/j.knosys.2021.107636
