Perspectiva del uso de energía eléctrica mediante redes neuronales
- Autores: José Rojas, Ricardo Luna
- Localización: Ciencias de la Ingeniería y Tecnología Handbook T-III: Congreso Interdisciplinario de Cuerpos Académicos / coord. por Joel Quintanilla Domínguez, José Miguel Barrón Adame, 2013, ISBN 978-607-8324-14-9, págs. 95-104
- Idioma: español
- Enlaces
-
Resumen
Demand for electricity in industrial, commercial and residential sectors represents a current problem to predict ahead of time electricity consumption in these sectors in order to avoid penalties imposed by the respective companies supplying electricity, plans to develop a system perspective electricity demand for intelligent buildings using artificial neural networks (ANN) that allows us a prediction of power consumption ahead of time, and therefore better management of energy in buildings. The variables used as inputs to the neural prediction model were: temperature and humidity, as well as power consumption and time. The algorithm used for perspective was Levenberg-Marquardt. The model validation was performed by comparing the results with a non-linear regression model and actual data with analysis of variance (ANOVA). The results of the 4-4-1 model prediction were 95% reliability.
