Artificial intelligence in forecasting demands for electricity : an application in optimization of energy resources

ABSTRACT: This paper presents a current application of neural networks in the task of forecasting electricity demands in Colombia. They are used networks of the Multi Layer Perceptron (MLP) type with backpropagation training algorithms, and Radial Basic Function (RBF). The information available with time and hourly values of demands in megawatts (MW) is organized in such a way that the task of forecasting raises a problem of classifying information where previous networks have shown good performance. The task of organizing information, training, validation and prognosis are developed with Matlab programming.

• Autores: Villa Acevedo, Walter Mauricio; Sarmiento Maldonado, Henry Omar
• Tipo de recurso: Article of investigation
• Fecha de publicación: 2008
• Institución: Universidad de Antioquia
• Repositorio: Repositorio UdeA
• Idioma: eng
• OAI Identifier: oai:bibliotecadigital.udea.edu.co:10495/36353
• Acceso en línea: https://hdl.handle.net/10495/36353; https://www.unipamplona.edu.co/unipamplona/portalIG/home_40/recursos/revistas/27102011/revista_12.jsp
• Palabra clave: Redes neuronales (Ciencias de la computación); Neural networks (Computer science); Inteligencia Artificial; Artificial intelligence; Sistemas de control feedforward; Feedforward control systems; Previsión; Forecasts; Sistemas de Energía Eléctrica; Electric power systems; http://id.loc.gov/authorities/subjects/sh90001937; http://id.loc.gov/authorities/subjects/sh85008180; http://id.loc.gov/authorities/subjects/sh85047652; http://id.loc.gov/authorities/subjects/sh85050485; http://id.loc.gov/authorities/subjects/sh85041921
• Rights: openAccess
• License: https://creativecommons.org/licenses/by-nc-nd/4.0/