Neural Systems for Short-Term Forecasting of Electric Power Load

  • Michał Ba̧k
  • Andrzej Bielecki
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4432)


In this paper a neural system for daily forecasting of electric power load in Poland is presented. Basing on the simplest neural architecture - a multi-layer perceptron - more and more complex system is built step by step. A committee rule-aided hierarchical system consisting of modular ANNs is obtained as a result. The forecasting mean absolute percentage error (MAPE) of the most effective system is about 1.1%.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Abdel-Aal, R.E., Al-Garni, A.Z.: Forecasting monthly electric energy consumption in eastern Saudi Arabia using univariate time-series analysis. Fuel and Energy Abstracts 38, 452–452 (1997)Google Scholar
  2. 2.
    Abdel-Aal, R.E., Al-Garni, A.Z., Al-Nassar, Y.N.: Modelling and forecasting monthly electric energy consumption in eastern Saudi Arabia using abductive networks. Energy 22, 911–921 (1997)CrossRefGoogle Scholar
  3. 3.
    Abdel-Aal, R.E.: Short-term hourly load forecasting using abductive networks. IEEE Transactions on Power Systems 19, 164–173 (2004)CrossRefGoogle Scholar
  4. 4.
    Abdel-Aal, R.E.: Improving electric load forecasts using network committees. Electric Power Systems Research 74, 83–94 (2005)CrossRefGoogle Scholar
  5. 5.
    Abdel-Aal, R.E.: Modeling and forecasting electric daily peak loads using abductive networks. International Journal of Electrical Power and Energy Systems 28, 133–141 (2006)CrossRefGoogle Scholar
  6. 6.
    Bartkiewicz, W.: Confidence intervals prediction for the short-term electrical load neural forecasting models. Elektrotechnik und Informationstechnik 117, 8–12 (2000)Google Scholar
  7. 7.
    Bielecki, A., Ba̧k, M.: Methodology of Neural Systems Development. In: Cader, A., Rutkowski, L., Tadeusiewicz, R., Żurada, J. (eds.) Artificial Intelligence and Soft Computing. Challanging Problems of Science - Computer Science, pp. 1–7. Academic Publishing House EXIT, Warszawa (2006)Google Scholar
  8. 8.
    Breiman, L.: Bagging predictors. Machine Learning 24, 123–140 (1996)zbMATHMathSciNetGoogle Scholar
  9. 9.
    Cottrell, M., Girard, B., Girard, Y., Muller, C., Rousset, P.: Daily electrical power curve: classification and forecasting using a Kohonen map. In: Sandoval, F., Mira, J. (eds.) IWANN 1995. LNCS, vol. 930, pp. 1107–1113. Springer, Heidelberg (1995)Google Scholar
  10. 10.
    Djukanowic, M., Babic, B., Sobajic, D.J., Pao, Y.H.: Unsupervised/supervised learning concept for 24-hour load forecasting. IEE Proceedings 4, 311–318 (1993)Google Scholar
  11. 11.
    Hsu, Y.Y., Ho, K.L.: Fuzzy expert systems: an application to short-term load forecasting. IEE Proceedings 6, 471–477 (1992)Google Scholar
  12. 12.
    Malko, J.: Certain Forecasting Problems in Electrical Power Engineering (in Polish). Oficyna Wydawnicza Politechniki Wrocławskiej, Wrocław (1995)Google Scholar
  13. 13.
    Marciniak, A., Korbicz, J.: Modular neural networks (in Polish). In: Duch, W., Korbicz, J., Rutkowski, L., Tadeusiewicz, R. (eds.) Neural Networks, Biocybernetics and Biomedical Engineering, vol. 6, pp. 135–178. Academic Publishing House EXIT, Warszawa (2000)Google Scholar
  14. 14.
    Osowski, S.: Neural Networks - an Algorithmic Approach (in Polish). WNT, Warszawa (1996)Google Scholar
  15. 15.
    Osowski, S.: Neural Networks for Information Processing (in Polish). Oficyna Wydawnicza Politechniki Warszawskiej, Warszawa (2000)Google Scholar
  16. 16.
    Osowski, S., Siwek, K.: Selforganizing neural networks for short term load forecasting in power system. In: Engineering Applications of Neural Networks, pp. 253–256 (1998)Google Scholar
  17. 17.
    Osowski, S., Siwek, K.: Regularization of neural networks for improved load forecasting in the power system. IEE Proc. Generation, Transmission and Distribution 149, 340–344 (2002)CrossRefGoogle Scholar
  18. 18.
    Osowski, S., Siwek, K., Tran Hoai, L.: Short term load forecasting using neural networks. In: Proc. III Ukrainian-Polish Workshop, Aluszta, Krym, pp. 72–77 (2001)Google Scholar
  19. 19.
    Park, D.C., El-Sharkawi, M.A., Marks, R.J., Atlas, R.E., Damborg, M.J.: Electric load forecasting using an artificial neural network. IEEE Transactions on Power Systems 6, 442–449 (1991)CrossRefGoogle Scholar
  20. 20.
    Peng, T.M., Hubele, N.F., Karady, G.G.: Advancement in the application of neural networks for short-term load forecasting. IEEE Transactions on Power Systems 7, 250–257 (1992)CrossRefGoogle Scholar
  21. 21.
    Siwek, K.: Load forecasting in an electrical power system using artificial neural networks. PhD Thesis (in Polish), Faculty of Electricity, Warsaw Technical University (2001)Google Scholar
  22. 22.
    Tresp, V.: Committee Machines. In: Hu, Y.H., Hwang, J.-N. (eds.) Handbook for Neural Network Signal Processing, CRC Press, Boca Raton (2001)Google Scholar
  23. 23.
    Weron, A., Weron, R.: Stock Market of Energy (in Polish). CIRE, Wrocław (2000)Google Scholar
  24. 24.
    Zieliński, J.S.: Intelligent Systems in Management - Theory and Practice (in Polish). PWN, Warszawa (2000)Google Scholar

Copyright information

© Springer Berlin Heidelberg 2007

Authors and Affiliations

  • Michał Ba̧k
    • 1
  • Andrzej Bielecki
    • 1
  1. 1.Institute of Computer Science, Jagiellonian University, Nawojki 11, 30-072 KrakówPoland

Personalised recommendations