Cascade correlation networks for electricity spot price forecasting in Brasil

Cascade correlation networks for electricity spot price forecasting in Brasil

The aim of this paper is to propose the use of regularized cascade correlation neural networks to forecast the monthly Brazilian electricity spot price. The cascade correlation models have been regularized with weight decay, weight elimination and ridge regression techniques, and several regularized models have been estimated. The results show that the regularized cascade correlation network represents the dynamic series better than other similar models such as the multilayer perceptron (MLP) and ARIMA. Then the regularized cascade correlation neural networks allow finding a suitable model to forecast the monthly Brazilian electricity spot price.

Saved in:
Bibliographic Details
Main Authors: Villa, Fernán, Velásquez, Juan
Format: Digital revista
Language:spa
Published: Universidad de Ciencias Aplicadas y Ambientales U.D.C.A 2011
Online Access:https://revistas.udca.edu.co/index.php/ruadc/article/view/793
Tags: Add Tag
No Tags, Be the first to tag this record!
id rev-ruadc-co-article-793
record_format ojs
institution UDCA CO
collection OJS
country Colombia
countrycode CO
component Revista
access En linea
databasecode rev-ruadc-co
tag revista
region America del Sur
libraryname Biblioteca de la UDCA de Colombia
language spa
format Digital
author Villa, Fernán
Velásquez, Juan
spellingShingle Villa, Fernán
Velásquez, Juan
Cascade correlation networks for electricity spot price forecasting in Brasil
author_facet Villa, Fernán
Velásquez, Juan
author_sort Villa, Fernán
title Cascade correlation networks for electricity spot price forecasting in Brasil
title_short Cascade correlation networks for electricity spot price forecasting in Brasil
title_full Cascade correlation networks for electricity spot price forecasting in Brasil
title_fullStr Cascade correlation networks for electricity spot price forecasting in Brasil
title_full_unstemmed Cascade correlation networks for electricity spot price forecasting in Brasil
title_sort cascade correlation networks for electricity spot price forecasting in brasil
description The aim of this paper is to propose the use of regularized cascade correlation neural networks to forecast the monthly Brazilian electricity spot price. The cascade correlation models have been regularized with weight decay, weight elimination and ridge regression techniques, and several regularized models have been estimated. The results show that the regularized cascade correlation network represents the dynamic series better than other similar models such as the multilayer perceptron (MLP) and ARIMA. Then the regularized cascade correlation neural networks allow finding a suitable model to forecast the monthly Brazilian electricity spot price.
publisher Universidad de Ciencias Aplicadas y Ambientales U.D.C.A
publishDate 2011
url https://revistas.udca.edu.co/index.php/ruadc/article/view/793
work_keys_str_mv AT villafernan cascadecorrelationnetworksforelectricityspotpriceforecastinginbrasil
AT velasquezjuan cascadecorrelationnetworksforelectricityspotpriceforecastinginbrasil
AT villafernan predicciondelpreciodelaelectricidadenbrasilusandoredescascadacorrelacion
AT velasquezjuan predicciondelpreciodelaelectricidadenbrasilusandoredescascadacorrelacion
_version_ 1763178474671964160
spelling rev-ruadc-co-article-7932021-07-13T07:56:25Z Cascade correlation networks for electricity spot price forecasting in Brasil Predicción del precio de la electricidad en Brasil usando redes cascada correlación Villa, Fernán Velásquez, Juan Pronóstico Redes neuronales Mercados liberalizados Forecasting Neural networks Liberalized markets The aim of this paper is to propose the use of regularized cascade correlation neural networks to forecast the monthly Brazilian electricity spot price. The cascade correlation models have been regularized with weight decay, weight elimination and ridge regression techniques, and several regularized models have been estimated. The results show that the regularized cascade correlation network represents the dynamic series better than other similar models such as the multilayer perceptron (MLP) and ARIMA. Then the regularized cascade correlation neural networks allow finding a suitable model to forecast the monthly Brazilian electricity spot price. En este artículo, se propone utilizar redes neuronales tipo cascada correlación regularizadas, para pronosticar el precio mensual, de corto plazo, de la electricidad del mercado brasileño. Se estiman diversos modelos de redes cascada correlación regularizados entre la capa de entrada y oculta, con descomposición o con eliminación de pesos, mientras que entre la capa oculta y la de salida, se regulariza con regresión de borde. Los resultados indican que las redes cascada correlación regularizadas en todas sus capas describen mejor la dinámica de la serie de precios que la misma red sin regularizar, que un modelo ARIMA y que un perceptrón multicapa (MLP) clásico, que usa los mismos rezagos y neuronas en la capa oculta, lo cual, permite afirmar, que para la serie de precios de electricidad, las redes cascada correlación regularizadas permiten encontrar modelos con mejor capacidad de pronóstico. Universidad de Ciencias Aplicadas y Ambientales U.D.C.A 2011-12-31 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf text/html https://revistas.udca.edu.co/index.php/ruadc/article/view/793 10.31910/rudca.v14.n2.2011.793 Revista U.D.C.A Actualidad & Divulgación Científica; Vol. 14 No. 2 (2011): Revista U.D.C.A Actualidad & Divulgación Científica. Julio-Diciembre; 161-167 Revista U.D.C.A Actualidad & Divulgación Científica; Vol. 14 Núm. 2 (2011): Revista U.D.C.A Actualidad & Divulgación Científica. Julio-Diciembre; 161-167 Revista U.D.C.A Actualidad & Divulgación Científica; v. 14 n. 2 (2011): Revista U.D.C.A Actualidad & Divulgación Científica. Julio-Diciembre; 161-167 2619-2551 0123-4226 10.31910/rudca.v14.n2.2011 spa https://revistas.udca.edu.co/index.php/ruadc/article/view/793/873 https://revistas.udca.edu.co/index.php/ruadc/article/view/793/874 /*ref*/ANGELUS, A. 2001. Electricity price forecasting in deregulated markets. The Electricity Journal (USA). 13(4):32-41. /*ref*/ARMSTRONG, M.; COWAN, S.; VICKERS, J. 1994. Regulatory Reform: Economic Analysis and British Experience. Ed. Cambridge: The MIT Press (USA). 392p. /*ref*/CONEJO, A.; CONTRERAS, J.; ESPÍNOSA, R.; PLAZAS, M. 2005. Forecasting electricity prices for a dayahead pool-based electric energy market. Internal J. Forecasting (USA). (21):435-462. /*ref*/DE MEDEIROS, L. 2004. Previs?o do Pre?o Spot no Mercado de Energia Elétrica. PhD thesis, Pontificia Universidade Católica do Rio de Janeiro. Disponible desde Internet en: http://www.maxwell.lambda.ele.puc-rio.br/ [con acceso el 02/10/2009]. /*ref*/F AHLMAN, S.E.; LEBIERE, C. 1990. The Cascade- Correlation Learning Architecture. Advances in Neural Information Processing Systems (USA). 2:524-532. /*ref*/GARETA, R.; GIL, A.; MONZÓN, A.; ROMEO, L. 2004. Las redes neuronales como herramienta para predecir el precio de la energía eléctrica. Energía: Revista de Ingeniería energética y medioambiental (España). 30(180):67-72. /*ref*/HINTON, G. 1989. Connectionist learning procedures. Artificial Intelligence (USA). (40):185-243. /*ref*/HIPPERT, H.; BUNN, D.; SOUZA, R. 2005. Large neural networks for electricity load forecasting: Are they overfitted? Internal J. Forecasting (USA). 21(3):425- 434. /*ref*/HOERL, A.E.; KENNARD, R.W. 1970. Ridge Regression: Biased Estimation for Nonorthogonal Problems. Technometrics (USA). 12(1):55-67. /*ref*/HYNDMAN, R.; KHANDAKAR, Y. 2008. Automatic time series forecasting: The forecast package for R. J. Statistical Software (USA). 26(3):1-22. /*ref*/LU, X.; DONG, Z.; LI, X. 2005. Electricity market price spike forecast with data mining techniques. Electric Power Systems Research (USA). 73(1):19-29. /*ref*/MARQUARDT, D.W.; SNEE, R.D. 1975. Ridge regression in practice. The American Statistician (USA). 29(1):3- 20. /*ref*/MASTERS, T. 1993. Practical neural network recipes in C++. Ed. New York: Academic Press (USA). 493p. /*ref*/PILIPOVIC, D. 1998. Energy Risk. Valuing and Managing Energy Derivatives. Ed. McGraw-Hill (USA). 64p. /*ref*/STEINER, F. 2000. Regulation, industry structure and performance in the electricity supply industry. OECD Economics Department Working Papers (Francia). 238:5-25. /*ref*/VELÁSQUEZ, J.D.; DYNER, I.; SOUSA, R.C. 2007. ¿Por qué es tan difícil obtener buenos pronósticos de los precios de la electricidad en mercados competitivos? Cuadernos de Administración (Colombia). 20:259- 282. /*ref*/VELÁSQUEZ, J.D.; VILLA, F.A.; SOUZA, R.C. 2010. Predicción de series de tiempo con redes cascadacorrelación. Ingeniería e Investigación (Colombia). 30(1):157-162. /*ref*/VELÁSQUEZ, J.D; DYNER, I.; SOUZA, R.C. 2008. Modelado del Precio Spot de la Electricidad en Brasil Usando una Red Neuronal Auto Regresiva. Ingeniare: Rev. Chilena de Ingeniería. 16(3):394-403. /*ref*/VILLA, F.A.; VELÁSQUES, J.D.; JARAMILLO, P. 2009. Conrprop: un algoritmo para la optimización de funciones no lineales con restricciones. Rev. Facultad de Ingeniería Universidad de Antioquia (Colombia). (50):188-194. /*ref*/VILLA, F.A.; VELÁSQUEZ, J.D.; SOUZA, R.C. 2008. Una aproximación a la regularización de redes cascadacorrelación para la predicción de series de tiempo. Investigación Operacional (Portugal). (28):151-161. /*ref*/WEIGEND, A.S.; RUMELHART, D.E.; HUBERMAN, B.A. 1991. Generalization by weight-elimination with application to forecasting. Advances in Neural Information Processing Systems (USA). 3:875-882. /*ref*/ZHANG, G.; PATUWO, B.E.; HU, M.Y. 1998. Forecasting with artificial neural networks: the state of the art. Internal J. Forecasting (USA). 14(1):35-62.

Similar Items