Can I read A Surrogate-assisted Differential Evolution for Expensive Constrained Optimization Problems Involving Mixed-integer Variables on EtoBox?

A Surrogate-assisted Differential Evolution for Expensive Constrained Optimization Problems Involving Mixed-integer Variables by Yuanhao Liu; Zan Yang; Danyang Xu; Haobo Qiu; Liang Gao is a Computer Science article available to read on EtoBox.

What is A Surrogate-assisted Differential Evolution for Expensive Constrained Optimization Problems Involving Mixed-integer Variables about?

Many Surrogate-Assisted Evolutionary Algorithms (SAEAs) have been developed for expensive constrained optimization problems (ECOPs) with continuous variables. However, there exist some ECOPs that contain mixed-integer variables in real world engineering applications. The mixed-integer variables make the feasible regions of ECOPs exhibit complex disjoint characteristics, which brings two challenges for the existing methods, i.e., the classical surrogate-assisted pre-screening may easily fall into a local optimum and the population diversity tends to reduce with the influence of integer variables. For tackling these problems, a surrogate-assisted differential evolution for solving ECOPs involving mixed-integer variables (SADE-MI) is proposed. Firstly, the mutation strategy DE/best/2 is used to balance the local and global characteristics of the candidate solutions. Secondly, an adaptive pre-screening operation where the information of the population is effectively employed to construct the distance constraints is designed to avoid excessive exploitation in local regions. Finally, by selecting diversely-located individuals and limiting the number of individuals with the same integer v

Who reads A Surrogate-assisted Differential Evolution for Expensive Constrained Optimization Problems Involving Mixed-integer Variables?

Author

Yuanhao Liu; Zan Yang; Danyang Xu; Haobo Qiu; Liang Gao

Publisher

Elsevier BV

Published

2023

Language

EN

Field

Computer Science (Physical Sciences)