Handling Dynamic Multiobjective Optimization Environments via Layered Prediction and Subspace-Based Diversity Maintenance

Yaru Hu, Jinhua Zheng* (Corresponding Author), Shouyong Jiang* (Corresponding Author), Shengxiang Yang, Juan Zou

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

In this article, we propose an evolutionary algorithm based on layered prediction (LP) and subspace-based diversity maintenance (SDM) for handling dynamic multiobjective optimization (DMO) environments. The LP strategy takes into account different levels of progress by different individuals in evolution and historical information to predict the population in the event of environmental changes for a prompt change response. The SDM strategy identifies gaps in population distribution and employs a gap-filling technique to increase population diversity. SDM further guides rational population reproduction with a subspace-based probability model to maintain the balance between population diversity and convergence in every generation of evolution regardless of environmental changes. The proposed algorithm has been extensively studied through comparison with five state-of-the-art algorithms on a variety of test problems, demonstrating its effectiveness in dealing with DMO problems.

Original languageEnglish
Number of pages14
JournalIEEE Transactions on Cybernetics
Early online date15 Dec 2021
DOIs
Publication statusE-pub ahead of print - 15 Dec 2021

Keywords

  • Change response
  • Convergence
  • dynamic multiobjective optimization (DMO)
  • gap filling
  • Heuristic algorithms
  • layered prediction (LP)
  • Linear programming
  • Maintenance engineering
  • Optimization
  • Sociology
  • Statistics
  • subspace-based diversity maintenance (SDM)

Fingerprint

Dive into the research topics of 'Handling Dynamic Multiobjective Optimization Environments via Layered Prediction and Subspace-Based Diversity Maintenance'. Together they form a unique fingerprint.

Cite this