Continuous dynamic constrained optimization-the challenges

Trung Thanh NGUYEN, Xin YAO

Research output: Journal PublicationsJournal Article (refereed)peer-review

94 Citations (Scopus)

Abstract

Many real-world dynamic problems have constraints, and in certain cases not only the objective function changes over time, but also the constraints. However, there is no research in answering the question of whether current algorithms work well on continuous dynamic constrained optimization problems (DCOPs), nor is there any benchmark problem that reflects the common characteristics of continuous DCOPs. This paper contributes to the task of closing this gap. We will present some investigations on the characteristics that might make DCOPs difficult to solve by some existing dynamic optimization (DO) and constraint handling (CH) algorithms. We will then introduce a set of benchmark problems with these characteristics and test several representative DO and CH strategies on these problems. The results confirm that DCOPs do have special characteristics that can significantly affect algorithm performance. The results also reveal some interesting observations where the presence or combination of different types of dynamics and constraints can make the problems easier to solve for certain types of algorithms. Based on the analyses of the results, a list of potential requirements that an algorithm should meet to solve DCOPs effectively will be proposed. © 2012 IEEE.
Original languageEnglish
Article number6148271
Pages (from-to)769-786
Number of pages18
JournalIEEE Transactions on Evolutionary Computation
Volume16
Issue number6
Early online date7 Feb 2012
DOIs
Publication statusPublished - Dec 2012
Externally publishedYes

Bibliographical note

This work was supported by an U.K. ORS Award, a studentship from the School of Computer Science, University of Birmingham, and two EPSRC Grants EP/E058884/1 and EP/D052785/1.

Keywords

  • Benchmark problems
  • constraint handling (CH)
  • dynamic constraints
  • dynamic environments
  • dynamic optimization (DO)
  • evolutionary algorithms
  • performance measures

Fingerprint

Dive into the research topics of 'Continuous dynamic constrained optimization-the challenges'. Together they form a unique fingerprint.

Cite this