Self-Adaptive Polynomial Mutation in Multi-Objective Evolutionary Algorithms
Evolutionary multi-objective optimization is a field that has experienced a rapid growth in the last two decades. Although an important number of new multi-objective evolutionary algorithms have been designed by the scientific community, the popular Non-Dominated Sorting Genetic Algorithm (NSGAII) r...
| Autor: | |
|---|---|
| Tipo de recurso: | tesis de maestría |
| Fecha de publicación: | 2022 |
| País: | España |
| Institución: | Universidad Nacional de Educación a Distancia |
| Repositorio: | e-spacio. Repositorio Institucional de la UNED |
| Idioma: | inglés |
| OAI Identifier: | oai:e-spacio.uned.es:20.500.14468/14657 |
| Acceso en línea: | https://hdl.handle.net/20.500.14468/14657 |
| Access Level: | acceso abierto |
| Palabra clave: | 1203.04 Inteligencia artificial multi-objective evolutionary algorithm NSGA-II polynomial mutation distribution index self-adaptation |
| Sumario: | Evolutionary multi-objective optimization is a field that has experienced a rapid growth in the last two decades. Although an important number of new multi-objective evolutionary algorithms have been designed by the scientific community, the popular Non-Dominated Sorting Genetic Algorithm (NSGAII) remains as a widely used baseline for performance comparison purposes. Since every evolutionary algorithm needs several parameters to be set up in order to operate, parameter control constitutes a crucial task for the effective and efficient performance of multi-objective evolutionary algorithms. However, despite the advancements in parameter control for evolutionary algorithms, NSGA-II has been mainly used in the literature with fine-tuned static parameters. This paper introduces a novel and computationally lightweight self-adaptation mechanism for controlling the distribution index parameter of the polynomial mutation operator usually employed by NSGA-II in particular and by multi-objective evolutionary algorithms in general. Additionally, the classical NSGA-II using polynomial mutation with a static distribution index is compared with this new version utilizing a self-adapted parameter. The experiments carried out over twenty-five benchmark problems using three quality indicators (hypervolume, generalized spread, and modified inverted generational distance) show that the proposed self-adaptive mutator variant outperforms its static counterpart in most of the cases. This result supports the potential of self-adaptive parameter control in multi-objective evolutionary algorithms. |
|---|