Forecasting the electricity load from one day to one week ahead for the Spanish system operator

This paper discusses the building process and models used by Red Electrica de Espana (REE), the Spanish system operator, in short-term electricity load forecasting. REE's forecasting system consists of one daily model and 24Â hourly models with a common structure. There are two types of forecasts of special interest to REE, several days ahead predictions for daily data, and one day ahead hourly forecasts. Accordingly, the forecast accuracy is assessed in terms of their errors. To do this, we analyse historical, real time forecasting errors for daily and hourly data for the year 2006, and report the forecasting performance by day of the week, time of the year and type of day. Other aspects of the prediction problem, like the influence of the errors in predicting the temperature on forecasting the load several days ahead, or the need for an adequate treatment of special days, are also investigated.

[1]  Regina Lamedica,et al.  A neural network based technique for short-term forecasting of anomalous load periods , 1996 .

[2]  E. Lawler,et al.  Empowering Service Employees , 1995 .

[3]  Georges A. Darbellay,et al.  Forecasting the short-term demand for electricity: Do neural networks stand a better chance? , 2000 .

[4]  E. Nevis,et al.  Understanding Organizations as Learning Systems , 1995 .

[5]  O. Hyde,et al.  An adaptable automated procedure for short-term electricity load forecasting , 1997 .

[6]  Remy Cottet,et al.  Bayesian Modeling and Forecasting of Intraday Electricity Load , 2003 .

[7]  J. W. Taylor,et al.  Short-term electricity demand forecasting using double seasonal exponential smoothing , 2003, J. Oper. Res. Soc..

[8]  Vitor Hugo Ferreira,et al.  Input space to neural network based load forecasters , 2008 .

[9]  P. McSharry,et al.  A comparison of univariate methods for forecasting electricity demand up to a day ahead , 2006 .

[10]  Antoni Espasa,et al.  Using high-frequency data and time series models to improve yield management , 2001, Int. J. Serv. Technol. Manag..

[11]  L. J. Soares,et al.  Forecasting electricity demand using generalized long memory , 2003 .

[12]  Henry E. Warren,et al.  Modeling the Impact of Summer Temperatures on National Electricity Consumption , 1981 .

[13]  G. Karady,et al.  Economic impact analysis of load forecasting , 1997 .

[14]  John Peirson,et al.  Non‐Linearities in Electricity Demand and Temperature: Parametric Versus Non‐Parametric Methods , 1997 .

[15]  R. Ramanathan,et al.  Short-run forecasts of electricity loads and peaks , 1997 .

[16]  Derek W. Bunn,et al.  Large neural networks for electricity load forecasting: Are they overfitted? , 2005 .

[17]  Á. Pardo,et al.  Temperature and seasonality influences on Spanish electricity load , 2002 .

[18]  Enric Valor,et al.  Daily Air Temperature and Electricity Load in Spain , 2001 .

[19]  A. Espasa,et al.  Modelling and forecastng daily series of electricity demand , 1996 .

[20]  M. Smith.  Modeling and Short-Term Forecasting of New South Wales Electricity System Load , 2000 .

[21]  J. Manuel Revuelta,et al.  Automatic modelling of daily series of economic activity , 1996 .

[22]  A. Harvey,et al.  Forecasting Hourly Electricity Demand Using Time-Varying Splines , 1993 .

[23]  A. A. Weiss,et al.  Semiparametric estimates of the relation between weather and electricity sales , 1986 .

[24]  Randall L. Schultz.  Fundamental aspects of forecasting in organizations , 1992 .