A Sensitivity Analysis of Critical Genetic Algorithm Parameters: Highway Alignment Optimization Case Study

Eungcheol Kim, Manoj K. Jha and Min-Wook Kang
Additional contact information
Eungcheol Kim: Department of Civil and Environmental Engineering, Incheon National University, Incheon, South Korea
Manoj K. Jha: Department of Civil Engineering, Morgan State University, Baltimore, MD, USA
Min-Wook Kang: Department of Civil Engineering, University of South Alabama, Mobile, AL, USA

International Journal of Operations Research and Information Systems (IJORIS), 2015, vol. 6, issue 1, 30-48

Abstract: Genetic Algorithms (GAs) have been applied in many complex combinatorial optimization problems and have been proven to yield reasonably good solutions due to their ability of searching in continuous spaces and avoiding local optima. However, one issue in GA application that needs to be carefully explored is to examine sensitivity of critical parameters that may affect the quality of solutions. The key critical GA parameters affecting solution quality include the number of genetic operators, the number of encoded decision variables, the parameter for selective pressure, and the parameter for non-uniform mutation. The effect of these parameters on solution quality is particularly significant for complex problems of combinatorial nature. In this paper the authors test the sensitivity of critical GA parameters in optimizing 3-dimensional highway alignments which has been proven to be a complex combinatorial optimization problem for which an exact solution is not possible warranting the application of heuristics procedures, such as GAs. If GAs are applied properly, similar optimal solutions should be expected at each replication. The authors perform several example studies in order to arrive at a general set of conclusions regarding the sensitivity of critical GA parameters on solution quality. The first study shows that the optimal solutions obtained for a range of scenarios consisting of different combinations of the critical parameters are quite close. The second study shows that different optimal solutions are obtained when the number of encoded decision variables is changed.

Date: 2015
References: Add references at CitEc
Citations:

Downloads: (external link)
http://services.igi-global.com/resolvedoi/resolve. ... 18/ijoris.2015010103 (application/pdf)

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:igg:joris0:v:6:y:2015:i:1:p:30-48

Access Statistics for this article

International Journal of Operations Research and Information Systems (IJORIS) is currently edited by John Wang

More articles in International Journal of Operations Research and Information Systems (IJORIS) from IGI Global
Bibliographic data for series maintained by Journal Editor ().