DOI:
https://doi.org/10.14483/23448393.3836Publicado:
2011-12-18Número:
Vol. 16 Núm. 2 (2011): Julio - DiciembreSección:
ArtículosMétodo para la Predicción de Demanda Mensual de Electricidad en Colombia utilizando Análisis Wavelet y Modelos Auto-regresivos No Lineales
A Method for the Monthly Electricity Demand Forecasting in Colombia based on Wavelet Analysis and a Nonlinear Autoregressive Model
Palabras clave:
predicción de carga eléctrica, modelo neuronal no lineal autoregresivo, predicción en series de tiempo, análisis con transformada wavelet (es).Palabras clave:
electric load forecasting, nonlinear autoregressive neural model, time series forecasting, wavelet transform analysis. (en).Descargas
Resumen (es)
En este artículo se propone un método para la predicción mensual de la demanda en el Sistema Interconectado Nacional Eléctrico de Colombia. El método realiza preprocesamiento de la serie de tiempo utilizando un análisis multiresolución mediante tranformada wavelet discreta; se presenta un estudio para la selección de la wavelet madre y su orden, asi como del nivel de descomposición. Dado que originalmente la serie tiene comportamiento no lineal, se utilizó igualmente un modelo no lineal autoregresivo. La predicción se obtiene añadiendo a la tendencia, el estimado obtenido con el residual de la serie combinado con otros componentes extraídos durante el preproceamiento.
Se incluye una revisión bibliográfica de investigaciones realizadas internacionalmente y en Colombia en relación a la aplicación de la transformada wavelet y el modelo autoregresivo no lineal a la predicción de energía eléctrica.
Resumen (en)
This paper proposes a monthly electricity forecast method for the National Interconnected System (SIN) of Colombia. The method preprocesses the time series using a Multiresolution Analysis (MRA) with Discrete Wavelet Transform (DWT); a study for the selection of the mother wavelet and her order, as well as the level decomposition was carried out. Given that original series follows a non-linear behaviour, a neural nonlinear autoregressive (NAR) model was used. The prediction was obtained by adding the forecast trend with the estimated obtained by the residual series combined with further components extracted from preprocessing.
A bibliographic review of studies conducted internationally and in Colombia is included, in addition to references to investigations made with wavelet transform applied to electric energy prediction and studies reporting the use of NAR in prediction
Referencias
C. J. C.J. Franco, J. D. Velásquez and Y. Olaya, “Caracterización de la demanda mensual de electricidad en Colombia usando un modelo de componentes no observables,” Cuadernos de Administración, Vol. 21, pp. 221-235, 2008.
R. Abdel-Aal, “Univariate modeling and forecasting of monthly energy demand time series using abductive and neural network,” Computers & Industrial Engineering, vol. 54, nº 4, pp. 903-917, 2008.
Y. Zhangang, C. Yanbo and K.W.E. Cheng, “Genetic algorithm-based RBF neural networks load forecasting model,” Power Engineering Society General Meeting, pp. 1-6, 2007.
J. D. Velásquez, C. J. Franco and H. A. García, “Un modelo no lineal para la predicción de la demanda,” Estudios Gerenciales, vol. 25, nº 112, pp. 37-54, 2009.
M. Ghiassi, D. K. Zimbra, and H. Saidane, “Medium term system load forecasting with a dynamic,” Electric Power Systems Research, vol. 76, nº 5, pp. 302-316, 2006.
V. M. Rueda Mejía, Predicción del Consumo de Energía en Colombia con Modelos no Lineales, Maestría tesis, Universidad Nacional de Colombia, Sede Medellín, 2011.
D. Benaouda and F. Murtagh, “Electricity Load Forecast using Neural Network Trained from Wavelet-Transformed Data,” IEEE International Conference on Engineering of Intelligent Systems, nº 1, pp. 1-6, 2006.
D. Benaouda, F. Murtagh, J.-L. Starck, and O. Renaud, “Wavelet-based nonlinear multiscale decomposition model for electricity load forecasting,” Neurocomputing, vol. 70, nº 1-3, pp. 139-154, 2006.
Y. Bi, J. Zhao, and D. Zhang, “Power load forecasting algorithm based on wavelet packet analysis,” PowerCon, vol. 1, pp. 987-990, 2004.
A. S. Pandey, D. Singh, and S. K. Sinha, “Intelligent hybrid wavelet models for short-term load forecasting,” Power Systems, vol. 25, nº 3, p. 1266–1273, 2010.
C. Xia, B. Lei, C. Rao,and Z. He, “Research on short-term load forecasting model based on wavelet,” Natural Computation, vol. 2, nº 3, p. 830–834, 2011.
L. A. Jiménez Fernández, Modelosavanzadospara la predicción a cortoplazo de la produccióneléctrica, Logroño: Universidad de La Rioja Servicio de Publicaciones, 2007.
E. González-Romera, M. Á. Jaramillo-Morán, and D. Carmona-Fernández, “Monthly Electric Energy Demand Forecasting Based on Trend Extraction,” IEEE Transactions on Power Systems, vol. 21, nº 4, pp. 1946-1953, 2006.
S. Mirasgedis et al., “Models for mid-term electricity demand forecasting incorporating weather,” Energy, vol. 31, nº 2-3, pp. 208-227, 2006.
D.J. Pedregal and J. R. Trapero, “Mid-term hourly electricity forecasting based on a multi-rate approach,” Energy Conversion and Management, vol. 51, nº 1, pp. 105-111, 2009.
Subdirección de PlaneaciónEnergética (UPME), “Plan Expansión de ReferenciaGeneración - Transmisión 2010-2024,” pp. 23-229, 2010.
V. M. Rueda, J. D. VelásquezHenao, and C. J. Franco Cardona, “Avancesrecientes en la predicción de la demanda de electricidadusandomodelos no lineales,” Dyna, nº 167, pp. 36-43, 2011.
C. Xia, J. Wang, and K. McMenemy, “Short, medium and long term load forecasting model and virtual load forecaster based on radial basis function neural networks,” International Journal of Electrical Power & Energy Systems, vol. 32, nº 7, pp. 743-750, 2010.
A. Azadeh, S. Ghaderi, and S. Sohrabkhani, “Forecasting electrical consumption by integration of Neural Network, time series and ANOVA,” Applied Mathematics and Computation, vol. 186, nº 2, pp. 1753-1761, 2007.
S. Medina and J. García, “Predicción de demanda de energía en Colombia mediante un sistema de inferenciadifuso neuronal,” RevistaEnergética, vol. 33, p. 15–24, 2005.
A. J. Rocha Reis and A. P. Alves da Silva, “Feature Extraction via Multiresolution Analysis for Short-Term Load Forecasting,” IEEE Transactions on Power Systems, vol. 20, nº 1, pp. 189-198, 2005.
N. Sinha, L. L. Lai, P. K. Ghosh, and Y. Ma, “Wavelet-GA-ANN Based Hybrid Model for Accurate Prediction of Short-Term Load Forecast,” International Conference on Intelligent Systems Applications to Power Systems, pp. 1-8, 2007.
N. Amjady and F. Keynia, “Short-term load forecasting of power systems by combination of wavelet transform and neuro-evolutionary algorithm,” Energy, vol. 34, nº 1, pp. 46-57, 2009.
T. Liu, “Research on the Electric Load Forecasting and Risk Assessment Based on Wavelet Neural Network,” Third International Symposium on Intelligent Information Technology Application, pp. 568-571, 2009.
Q. Zhang, “Research on short-term electric load forecasting based on fuzzy rules and wavelet neural network,” 2nd International Conference on Computer Engineering and Technology, vol. 3, pp. 343-347, 2010.
Q. Zhang and T. Liu, “A Fuzzy Rules and Wavelet Neural Network Method for Mid-long-term Electric Load Forecasting,” Second International Conference on Computer and Network Technology, pp. 442-446, 2010.
J. T. Connor, R. D. Martin, and L. E. Atlas, “Recurrent neural networks and robust time series prediction,” IEEE transactions on neural networks, vol. 5, nº 2, pp. 240-254, 1994.
T. W. Chow and C.-T. Leung, “Nonlinear autoregressive,” IEE Proc.-Gener. Transm. Distrib., vol. 143, nº 5, pp. 500-506, 1996.
T. W. Chow and C.-T. Leung, “Nonlinear autoregressive integrated neural network model for short-term load forecasting,” IEEE Transactions on Power Systems, vol. 11, nº 4, p. 1736–1742, 1996.
L. Gang and F. Yu, “A hybrid nonlinear autoregressive neural network for permanent-magnet linear synchronous motor identification,” Machines and Systems, vol. 1, pp. 310 - 314, 2005.
P. Amani, M. Kihl, and A. Robertsson, “Multi-step ahead response time prediction for single server queuing systems,” Computers and Communications (ISCC), pp. 950 - 955, 2011.
S. Joekes, E. P. Barbosa, and W. Robledo, “Modelado y pronostico de unaserie de tiempocontaminadaempleandoredesneuronales y procedimientosestadísticostradicionales,” Revista de la Sociedad Argentina de Estadística, vol. 9, pp. 1-20, 2005.
E. Pisoni, M. Farina, C. Carnevale, and L. Piroddi, “Forecasting peak air pollution levels using NARX models,” Engineering Applications of Artificial Intelligence, vol. 22, nº 4-5, pp. 593-602, 2009.
E. Safavieh, S. Andalib, and A. Andalib, “Forecasting the Unknown Dynamics in NN3 Database Using a Nonlinear Autoregressive Recurrent Neural Network,” International Joint Conference on Neural Networks, pp. 2105-2109, 2007.
L. Gang, L. Zhiming, F. Yu, and L. Guo-guo, “Modeling of permanent-magnet linear synchronous motor using hybrid nonlinear autoregressive neural network,” 9th International Conference on Signal Processing, vol. 1, nº 2, pp. 1685-1689, 2008.
H. T. Pham, V. T. Tran, and B.-S. Yang, “A hybrid of nonlinear autoregressive model with exogenous input and autoregressive moving average model for long-term machine state forecasting,” Expert Systems with Applications, vol. 37, nº 4, pp. 3310-3317, 2010.
G. Mustafaraj, G. Lowry, and J. Chen, “Prediction of room temperature and relative humidity by autoregressive linear and nonlinear neural network models for an open office,” Energy and Buildings, vol. 43, nº 6, pp. 1452-1460, 2011.
I. Kaastra and M. Boyd, “Designing a neural network for forecasting financial and economic time series,” Neurocomputing, vol. 10, pp. 215-236, 1996.
E. Rivas, J.C. Burgos and J.C. García-Prada, “Condition Assessment of Power OLTC by Vibration Analysis Using Wavelet Transform,” IEEE Transactions on Power Delivery, vol. 24, nº 2, pp. 687-694, 2009.
L. P. Calôba, IntroduçãoaoUso de RedesNeuraisnaModelagem de SistemasDinâmicos e SériesTemporais., Natal: Livro de Minicursos do XIV CongressoBrasileiro de Automática, 2002.
M. Hudson Beale, M. T. Hagan, and H. B. Demuth, Neural Network Toolbox ™ 7 User ’ s Guide, The MathWorks, Inc., 2010.
Cómo citar
APA
ACM
ACS
ABNT
Chicago
Harvard
IEEE
MLA
Turabian
Vancouver
Descargar cita
Licencia
A partir de la edición del V23N3 del año 2018 hacia adelante, se cambia la Licencia Creative Commons “Atribución—No Comercial – Sin Obra Derivada” a la siguiente:
Atribución - No Comercial – Compartir igual: esta licencia permite a otros distribuir, remezclar, retocar, y crear a partir de tu obra de modo no comercial, siempre y cuando te den crédito y licencien sus nuevas creaciones bajo las mismas condiciones.