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