Hiperheurística basada en razonamiento con dominio en metaheurísticas X-PSO multiobjetivo hy X-FPSO CBR : aplicación sobre una optimización dinámica posibilística. Parte 1 : desarrollos teóricos del algoritmo hiperheurístico HY X-FPSO CBR
Date
2013-11
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
En el presente trabajo se desarrolla el marco conceptual/teórico relativo a una novedosa HiperHeurística, basada en Razonamiento y aplicada en el dominio de MetaHeurísticas variantes de la Optimización Por Enjambre de Partículas (PSO), denominadas X-PSO, MultiObjetivo. Esta HiperHeurística, referida como HY X-FPSO CBR (Case Based Reasoning) emplea, como mecanismo de selección de la forma X de la MetaHeurística FPSO a ser aplicada en cierta instancia de decisión, una Función de Elección aproximada
mediante una Red Neuronal Artificial tipo Retropropagación. Para el diseño y, particularmente, entrenamiento de la misma, son considerados aspectos relativos a los Principios de la Inteligencia de Grupo y las habilidades que cada forma X-FPSO exhibe para satisfacerlos, así como las características del Espacio de Búsqueda, inherentes a la Clase de Problemas que deben resolverse mediante la HiperHeurística propuesta: Establecer el Espacio de Estados requerido por una Optimización Dinámica Posibilística sobre la Planificación de Mediano/Corto Plazo de un Sistema de Distribución de Energía
Eléctrica (SDEE).
In this work the conceptual/theoretical framework of a novel HyperHeuristic, Case Based Reasoning and supported on some variants of MultiObjective Particle Swarm Optimization MetaHeuristic, called X-PSO, are presented. This HyperHeuristic, referred as HY X-FPSO CBR (Case Based Reasoning), works by mean of selection function, aproximated with an Artificial Backporpagation Neural Network. To design and, especially, training the Artificial Neural Network, Swarm Intelligence Principles and the skill that each X FPSO form exhibit to satisfy it, as well as the Search Space that is defined by the Problems Class to solve, are considered. This HyperHeuristic are designed to be applied in the definition of States Space required for a Possibilistic Optimization on the Mid/Short term Planning of a Electric Distribution System (EDS).
In this work the conceptual/theoretical framework of a novel HyperHeuristic, Case Based Reasoning and supported on some variants of MultiObjective Particle Swarm Optimization MetaHeuristic, called X-PSO, are presented. This HyperHeuristic, referred as HY X-FPSO CBR (Case Based Reasoning), works by mean of selection function, aproximated with an Artificial Backporpagation Neural Network. To design and, especially, training the Artificial Neural Network, Swarm Intelligence Principles and the skill that each X FPSO form exhibit to satisfy it, as well as the Search Space that is defined by the Problems Class to solve, are considered. This HyperHeuristic are designed to be applied in the definition of States Space required for a Possibilistic Optimization on the Mid/Short term Planning of a Electric Distribution System (EDS).
Description
Keywords
Optimización, Enjambre de partículas, HiperHeurísticas, Redes neuronales artificiales, Sistema de distribución de energía eléctrica, Optimization, Particles swarm, HyperHeuristics, Artificial neural network, Electric distribution system
Citation
Revista de la Escuela de Perfeccionamiento en Investigación Operativa XXI (34): 8-29 (2013)
Collections
Endorsement
Review
Supplemented By
Referenced By
Creative Commons license
Except where otherwised noted, this item's license is described as info:eu-repo/semantics/openAccess