Hyperheuristic model hy x-fpso cbr sii supported in metaheuristics x-pso multiobjective to solve a class of problems of combinatorial optimization
Selection HyperHeuristics are informed search methods that work in a higher abstraction level than heuristic or MetaHeuristics: they constitute heuristics to choose heuristics. Such selection is realized by a Choice Function (CF), whose target is to decide which heuristic strategy is applied in each...
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Artículo revista |
| Lenguaje: | Español |
| Publicado: |
Escuela de Perfeccionamiento en Investigación Operativa
2018
|
| Materias: | |
| Acceso en línea: | https://revistas.unc.edu.ar/index.php/epio/article/view/22200 |
| Aporte de: |
| Sumario: | Selection HyperHeuristics are informed search methods that work in a higher abstraction level than heuristic or MetaHeuristics: they constitute heuristics to choose heuristics. Such selection is realized by a Choice Function (CF), whose target is to decide which heuristic strategy is applied in each decision instance of the algorithm, using for that non-domain data about the problem being solved. In this work a Case Based Reasoning Selection HyperHeuristic with X-PSO MultiObjective domain is presented, whose CF is constituted of a Feed-Forward Artificial Neural Network (ANN) of Multi-Layer Perceptron (MLP) type. The non-domain information used by the CF is composed of Swarm Intelligence Indicators, proposed by the authors in previous papers, which aims to give a measure on the abilities of a swarm to solve a particular problem. The design and the optimization problem associated to the CF Case Based Training are presented, so as the method to carry out such training. Finally, the process is applied to build a CF for a CBR Hyperheuristic that solves two Combinatorial Optimization Problems: the Load Balancing of a Three Phase Power Distribution System and the Reliability Optimization of Electrical Distribution Systems in Medium-Voltage. |
|---|