Forecasting daily urban electric load profiles using artificial neural networks

Abstract

The paper illustrates a combined approach based on unsupervised and supervised neural networks for the electric energy demand forecasting of a suburban area with a prediction time of 24 h. A preventive classification of the historical load data is performed during the unsupervised stage by means of a Kohonen's self organizing map (SOM). The actual forecast is obtained using a two layered feed forward neural network, trained with the back propagation with momentum learning algorithm. In order to investigate the influence of climate variability on the electricity consumption, the neural network is trained using weather data (temperature, relative humidity, global solar radiation) along with historical load data available for a part of the electric grid of the town of Palermo (Italy) from 2001 to 2003. The model validation is performed by comparing model predictions with load data that were not used for the network's training. The results obtained bear out the suitability of the adopted methodology for the short term load forecasting (STLF) problem also at so small a spatial scale as the suburban one.