This paper presents artificial neural networks (ANN) evolved by a genetic a
lgorithm for short-term load forecasting. Using real load values and foreca
st weather data these ANN have been tested for electric load forecasting on
weekdays and weekends. For each day type, the best-evolved artificial neur
al network was found capable of accurately forecasting one-day ahead hourly
loads. The forecasting results obtained using these best-evolved networks
were observed to be consistently superior compared to a commonly used stati
stical method. (C) 1998 Elsevier Science B.V. All rights reserved.