Penalty and prediction methods for dynamic constrained multi-objective optimization

•Novel penalty and prediction methods based on MOEA named NDCMOEA are proposed.•A new penalty function for constraint handling is introduced.•An IGPM predictor is applied to predict an initial population when a change occurs.•NDCMOEA is very competitive at tracking the changing POS. Dynamic constrai...

Full description

Bibliographic Details

Published in:	Swarm and evolutionary computation Vol. 80; p. 101317
Main Authors:	Wang, Fengxia, Huang, Min, Yang, Shengxiang, Wang, Xingwei
Format:	Journal Article
Language:	English
Published:	Elsevier B.V 01.07.2023
Subjects:	Dynamic constrained multi-objective optimization problems Inverse Gaussian process model Penalty function Test instances Test instances Penalty function Inverse Gaussian process model Dynamic constrained multi-objective optimization problems
ISSN:	2210-6502
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!