Sixteen electric utilities surveyed state that use of ANNs significantly reduced errors in daily electric load forecasts, while only three found otherwise. Data for five gas utilities reinforces this result: the mean absolute percentage error (MAPE) for ANN daily gas demand forecasts was 6.4%, a 1.9% improvement over previous methods. Yet ANNs were not always best, implying opportunities for further improvement. The economic value of error reduction for electric utilities was assessed by examining operating decisions. For 19 utilities surveyed, an average of $800 000/year per utility is estimated to be saved from use of ANN-based forecasts. Most benefits resulted from improved generating unit scheduling; the utilities estimated such benefits to be up to $143 annually per peak MW of demand for each 1% improvement in MAPE. This estimated worth of accuracy improvement (roughly 0.1% of annual generation O&M costs) is confirmed by solving generation scheduling and dispatch models under various levels of forecast accuracy.

A key component of the daily operation and planning activities of an electric utility is short-term load forecasting, i.e., the prediction of hourly loads (demand) for the next hour to several days out. The accuracy of such forecasts has significant economic impact for the utility. This paper describes a load forecasting system known as ANNSTLF (artificial neural-network short-term load forecaster) which has received wide acceptance by the electric utility industry and presently is being used by 32 utilities across the USA and Canada. ANNSTLF can consider the effect of temperature and relative humidity on the load. Besides its load forecasting engine, ANNSTLF contains forecasters that can generate the hourly temperature and relative humidity forecasts needed by the system. ANNSTLF is based on a multiple ANN strategy that captures various trends in the data. Both the first and the second generation of the load forecasting engine are discussed and compared. The building block of the forecasters is a multilayer perceptron trained with the error backpropagation learning rule. An adaptive scheme is employed to adjust the ANN weights during online forecasting. The forecasting models are site independent and only the number of hidden layer nodes of ANN's need to be adjusted for a new database. The results of testing the system on data from ten different utilities are reported.

Advantages and disadvantages of expert systems are discussed. An overview of expert system applications being developed or considered high potential is given.>