A novel model for short term load forecasting of Iran power network by using Kohonen Neural Networks

This paper presents a novel model for short term forecasting of daily electrical load curve in power systems by using of two Kohonen Neural Networks (KNNs). The proposed model is sensitive to atmospheric factors such as temperature. In addition it is able to forecast normal and abnormal days of year such as holidays, ceremonies, religious and etc, with high accuracy. Ten models are considered for forecasting each day of week, special holidays, the days before special holidays and the days after special holidays In structure of each model, two KNNs are used. This model is tested with load and temperature information of Iran Power Network and MAD for non special days at years of 2002, 2003 and 2004 is 1.73%, 1.68% and 1.57%. Performance studies results show that the proposed model is very accurate.