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

[1]  S. Tsuzuki,et al.  An artificial neural-net based technique for power system dynamic stability with the Kohonen model , 1991, [Proceedings] Conference Papers 1991 Power Industry Computer Application Conference.

[2]  Herbert Müller,et al.  Energieprognose Mittels Neuraler Netzwerkkonzepte , 1995 .

[3]  S. J. Kiartzis,et al.  Short term load forecasting using fuzzy neural networks , 1995 .

[4]  Grégoire Mercier,et al.  Estimation and monitoring of bare soil/vegetation ratio with SPOT VEGETATION and HRVIR , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[5]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .

[6]  A. J. Germond,et al.  Application of the Kohonen network to short-term load forecasting , 1993, [1993] Proceedings of the Second International Forum on Applications of Neural Networks to Power Systems.

[7]  Leyan Xu,et al.  Artificial neural network short-term electrical load forecasting techniques , 1999, Proceedings of IEEE. IEEE Region 10 Conference. TENCON 99. 'Multimedia Technology for Asia-Pacific Information Infrastructure' (Cat. No.99CH37030).

[8]  H. Mori,et al.  A precondition technique with reconstruction of data similarity based classification for short-term load forecasting , 2004, IEEE Power Engineering Society General Meeting, 2004..

[9]  M. Verleysen,et al.  Double quantization forecasting method for filling missing data in the CATS time series , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).