Including preferences into a multiobjective evolutionary algorithm to deal with many-objective engineering optimization problems
In this paper, we introduce a new preference relation based on a reference point approach. This relation offers an easy approach to integrate decision maker’s preferences into a Multiobjective Evolutionary Algorithm (MOEA) without mod- ifying its basic structure. Besides finding the optimal solution...
| Autores: | , |
|---|---|
| Tipo de recurso: | artículo |
| Estado: | Versión publicada |
| Fecha de publicación: | 2014 |
| País: | México |
| Institución: | Universidad Autónoma Metropolitana |
| Repositorio: | Concentración de Recursos de Información Científica y Académica, UAM Cuajimalpa |
| Idioma: | inglés |
| OAI Identifier: | oai:ilitia.cua.uam.mx:123456789/17 |
| Acceso en línea: | http://ilitia.cua.uam.mx:8080/jspui/handle/123456789/17 |
| Access Level: | acceso abierto |
| Palabra clave: | info:eu-repo/classification/cti/7 Computación Evolutiva Optimización Multiobjetivo Métodos de Optimización Interactiva |
| Sumario: | In this paper, we introduce a new preference relation based on a reference point approach. This relation offers an easy approach to integrate decision maker’s preferences into a Multiobjective Evolutionary Algorithm (MOEA) without mod- ifying its basic structure. Besides finding the optimal solution of the achievement scalarizing function, the new preference relation allows the decision maker to find a set of solutions around that optimal solution. Then, a MOEA equipped with the proposed preference relation can be integrated into an interactive optimization method. One of the main advantages of the new method is that setting its parameters is an intuitive task to the decision maker. The other advantage is that, since our preference relation induces a finer order on vectors of objective space than that achieved by the Pareto dominance relation, it is appropriate to cope with problems having a high number of objectives. |
|---|