A novel hybrid multi-objective metamodel-based evolutionary optimization algorithm

Enrique Gabriel Baquela and Ana Carolina Olivera

Operations Research Perspectives, 2019, vol. 6, issue C

Abstract: Optimization via Simulation (OvS) is an useful optimization tool to find a solution to an optimization problem that is difficult to model analytically. OvS consists in evaluating potential solutions through simulation executions; however, its high computational cost is a factor that can make its implementation infeasible. This issue also occurs in multi-objective problems, which tend to be expensive to solve. In this work, we present a new hybrid multi-objective OvS algorithm, which uses Kriging-type metamodels to estimate the simulations results and a multi-objective evolutionary algorithm to manage the optimization process. Our proposal succeeds in reducing the computational cost significantly without affecting the quality of the results obtained. The evolutionary part of the hybrid algorithm is based on the popular NSGA-II. The hybrid method is compared to the canonical NSGA-II and other hybrid approaches, showing a good performance not only in the quality of the solutions but also as computational cost saving.

Keywords: Optimization via simulation; Metamodel; Multi-Objective optimization; Kriging; NSGA-II (search for similar items in EconPapers)
Date: 2019
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S221471601830068X
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:oprepe:v:6:y:2019:i:c:s221471601830068x

DOI: 10.1016/j.orp.2019.100098

Access Statistics for this article

Operations Research Perspectives is currently edited by Rubén Ruiz Garcia

More articles in Operations Research Perspectives from Elsevier
Bibliographic data for series maintained by Catherine Liu ().