Short-term electric load forecasting using ANN based trends combination model

This paper presents a novel approach to ANN based short-term load forecasting by decomposing the underlying relationships between load and weather variables into three main trends of weekly, daily and hourly. Each trend is captured by a separate ANN. The forecasts yielded by individual ANNs are then combined by another ANN to arrive at the final forecast. The performances of the proposed model and the traditional model are compared on the basis of one-week-ahead hourly forecasts. Results indicate that the proposed ANN based model can achieve greater forecasting accuracy than the traditional ANN based model.