MODELO BASEADO EM COMBINAÇÃO DE PREVISORES PARA PREVISÃO DE SÉRIES TEMPORAIS DE CARGA ELÉTRICA MODEL BASED ON COMBINATION OF PREDICTORS FOR SHORT-TERM LOAD FORECAST

The forecasting of load demand is a fundamental task for the proper functioning of electrical systems, because many decision-making processes such as planning, operation, security analysis and market decisions are highly influenced by this process. Knowing that meet the demand charge is a stochastic process, this prediction proves important to a energy company to operate safely and economically. From this viewpoint, this paper proposes the development of a methodology for load forecasting in the short term, based on a combination of several different predictors. The results showed that the combination of the predictors presented in most cases examined, more accurate results when compared to results obtained for only a forecast component individually. In this model, the forecast of the load demand curve was based on demand curves for known days.

[1]  Ying Chen,et al.  Short-Term Load Forecasting: Similar Day-Based Wavelet Neural Networks , 2010, IEEE Transactions on Power Systems.

[2]  Takaaki Ohishi,et al.  Ensembles of Selected and Evolved Predictors using Genetic Algorithms for Time Series Prediction , 2006, 2006 IEEE International Conference on Evolutionary Computation.

[3]  Lars Kai Hansen,et al.  Neural Network Ensembles , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Marcelo Augusto Cicogna.  Sistema de suporte a decisão para o planejamento e a programação da operação de sistemas de energia eletrica , 2003 .

[5]  Takaaki Ohishi,et al.  A Hybrid Ensemble Model Applied to the Short-Term Load Forecasting Problem , 2006, The 2006 IEEE International Joint Conference on Neural Network Proceedings.

[6]  N. Draper,et al.  Applied Regression Analysis , 1966 .

[7]  Yan Li,et al.  Selective ensemble using discrete differential evolution algorithm for short-term load forecasting , 2009, 2009 International Conference on Machine Learning and Cybernetics.

[8]  G. Gross,et al.  Short-term load forecasting , 1987, Proceedings of the IEEE.

[9]  S. Osowski,et al.  Short Term Load Forecasting Model in the Power System Using Ensemble of Predictors , 2007, 2007 IEEE Instrumentation & Measurement Technology Conference IMTC 2007.

[10]  R. Bastos,et al.  Improvement of the Short Term Load Forecasting Through the Similarity Among Consumption Profiles , 2009, IEEE Latin America Transactions.

[11]  John R. Koza,et al.  Genetic programming - on the programming of computers by means of natural selection , 1993, Complex adaptive systems.

[12]  C. S. Ozveren,et al.  Short term electric load forecast using artificial neural networks , 1994, Proceedings of MELECON '94. Mediterranean Electrotechnical Conference.