Advertisement

Daily electrical power curves: Classification and forecasting using a Kohonen map

  • Marie Cottrell
  • Bernard Girard
  • Yvonne Girard
  • Corinne Muller
  • Patrick Rousset
Neural Networks for Communications and Control
Part of the Lecture Notes in Computer Science book series (LNCS, volume 930)

Abstract

This paper addresses an extensively studied problem: how to forecast the daily half-hour electrical power curve. Many methods have been developed, classical linear methods (like ARIMA methods) as well as neural ones. In this paper, we present a very simple method: the past daily curves are normalized and one considers the corresponding profile (with mean 0 and variance 1). These profiles are classified using a Kohonen map. Then, for some future point, a strategy is defined in order to compute its typical profile, the mean and the variance are forecast and the expected power curve is computed. This method uses little computation time and is easy to develop. The first results are satisfactory and promising.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    R.Capone, S.Kimbrough, Using a neural network to predict electricity generation, Proc. WCNN 94, San Diego, pp. I-324–329, 1994.Google Scholar
  2. [2]
    M.Cottrell, B.Girard, Y.Girard, M.Mangeas, Time serires and neural networks: a statistical method for weight elimination, Proc. of ESANN 93, M.Verleysen Ed., Editions Quorum, (ISBN 2-9600049-0-6), 1993.Google Scholar
  3. [3]
    M.Cottrell, B.Girard, Y.Girard, M.Mangeas, C.Muller, Neural modeling for time series: a statistical stepwise method for weight elimination, IEEE Transactions on Neural Networks, in press, Prepublication SAMOS No. 20., 1993.Google Scholar
  4. [4]
    A.Garcia Tejedor, M.Cosculluela, C.Bermejo, R.Montes, A neural system for short-term load forecasting based on day-type classification, to appear in Proc. ISAP 94, 1994Google Scholar
  5. [5]
    K.L.Ho, Y.Y.Hsu, C.C.Yang, Short term forecasting using a multilayer neural network with an adaptative learning algorithm, Transactions on Power Systems, Vol. 7, No. 1, pp. 141–149, 1992Google Scholar
  6. [6]
    K.Y.Lee, Y.T.Cha, J.H.Park, Short-term load forecasting using an artificial neural network, Transactions on Power Systems, Vol. 7, No. 1, pp. 124–131, 1992.Google Scholar
  7. [7]
    C.Muller, M.Cottrell, B.Girard, Y.Girard, M.Mangeas, A neural network tool for forecasting french electricity consumption, Proc. WCNN 94, San Diego, pp. I-360–365, 1994.Google Scholar
  8. [8]
    Q. Yao, H. Tong, Quantifying the influence of initial values on nonlinear prediction, Technical Report, No. UKC/IMS/S92/5c, University of Kent, U.K., 1992.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1995

Authors and Affiliations

  • Marie Cottrell
    • 1
  • Bernard Girard
    • 1
  • Yvonne Girard
    • 1
  • Corinne Muller
    • 2
  • Patrick Rousset
    • 1
  1. 1.SAMOS Université Paris 1Paris Cedex 13France
  2. 2.Direction des Etudes et RecherchesElectricité de FranceClamartFrance

Personalised recommendations