Servicios Personalizados
Revista
Articulo
Indicadores
- Citado por SciELO
- Accesos
Links relacionados
- Citado por Google
- Similares en SciELO
- Similares en Google
Compartir
Revista Facultad de Ingeniería Universidad de Antioquia
versión impresa ISSN 0120-6230versión On-line ISSN 2422-2844
Resumen
TABARES, Héctor y HERNANDEZ, Jesús. Typical demand curvs of electric power for the residential, commercial and industrial sector of Medellin, using artificial neural networks and algorithms of interpolation. Rev.fac.ing.univ. Antioquia [online]. 2008, n.46, pp.110-118. ISSN 0120-6230.
One of the main problems for modeling the electric power consumption in a certain place is the extraction of the knowledge when it is stored in big volumes of information like for example historical registrations. According with this representation, each fact happened and registered consists of a couple of components (t, P) where t represents the time of sample registration and P the electric power consumed at that time. The daily registration has N cases that each of the well-known stimulus-answer couples represents. The objective of this work is to develop a function that allows finding the vector of entrance variables t to the vector of exit variables P. F is any function, in this case the electric power consumption. Their modeling with Artificial Neural Netwok (ANN) is Multi a Perceptron Layer (PMC). Another form of modeling it is using Interpolation Algorithms(AI).
Palabras clave : Artificial neural networks; interpolation algorithms; electric power demand.