Chapter

Advances in Computation and Intelligence

Volume 4683 of the series Lecture Notes in Computer Science pp 547-557

On the Performance of Metamodel Assisted MOEA/D

  • Wudong LiuAffiliated withDepartment of Computer Science, University of Essex
  • , Qingfu ZhangAffiliated withDepartment of Computer Science, University of Essex
  • , Edward TsangAffiliated withDepartment of Computer Science, University of Essex
  • , Cao LiuAffiliated withFaculty of Computer Science, China University of Geosciences
  • , Botond VirginasAffiliated withBT Research Laboratories

* Final gross prices may vary according to local VAT.

Get Access

Abstract

MOEA/D is a novel and successful Multi-Objective Evolutionary Algorithms(MOEA) which utilises the idea of problem decomposition to tackle the complexity from multiple objectives. It shows better performance than most nowadays mainstream MOEA methods in various test problems, especially on the quality of solution’s distribution in the Pareto set. This paper aims to bring the strength of metamodel into MOEA/D to help the solving of expensive black-box multi-objective problems. Gaussian Random Field Metamodel(GRFM) is chosen as the approximation method. The performance is analysed and compared on several test problems, which shows a promising perspective on this method.