Electricity Load Forecasting: A Weekday-Based Approach

  • Irena Koprinska
  • Mashud Rana
  • Vassilios G. Agelidis
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7553)


We present a new approach for building weekday-based prediction models for electricity load forecasting. The key idea is to conduct a local feature selection using autocorrelation analysis for each day of the week and build a separate prediction model using linear regression and backpropagation neural networks. We used two years of 5-minute electricity load data for the state of New South Wales in Australia to evaluate performance. Our results showed that the weekday-based local prediction model, when used with linear regression, obtained a small and statistically significant increase in accuracy in comparison with the global (one for all days) prediction model. Both models, local and global, when used with linear regression were accurate and fast to train and are suitable for practical applications.


electricity load forecasting autocorrelation analysis linear regression backpropagation neural networks weekday-based prediction model 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Taylor, J.W.: An evaluation of methods for very short-term load forecasting using minite-by-minute British data. International Journal of Forecasting 24, 645–658 (2008)CrossRefGoogle Scholar
  2. 2.
    Taylor, J.W.: Short-term electricity demand forecasting using double seasonal exponencial smoothing. Journal of the Operational Research Society 54, 799–805 (2003)CrossRefzbMATHGoogle Scholar
  3. 3.
    Taylor, J.W.: Triple seasonal methods for short-term electricity demand forecasting. European Journal of Operational Research 204, 139–152 (2010)CrossRefzbMATHGoogle Scholar
  4. 4.
    Charytoniuk, W., Chen, M.-S.: Very short-term load forecasting using artificial neutal networks. IEEE Transactions on Power Systems 15, 263–268 (2000)CrossRefGoogle Scholar
  5. 5.
    Shamsollahi, P., Cheung, K.W., Chen, Q., Germain, E.H.: A neural network based VSTLF for the interim ISO New England electricity market system. In: 22nd IEEE PICA Conf., pp. 217–222 (2001)Google Scholar
  6. 6.
    Sood, R., Koprinska, I., Agelidis, V.: Electricity load forecasting based on autocorrelation analysis. In: International Joint Conference on Neural Networks (IJCNN), Barcelona, pp. 1772–1779 (2010)Google Scholar
  7. 7.
    Koprinska, I., Rana, M., Agelidis, V.: Yearly and Seasonal Models for Electricity Load Forecasting. In: International Joint Conference on Neural Networks (IJCNN 2011), USA (2011)Google Scholar
  8. 8.
    Chen, B.J., Chang, M.-W., Lin, C.-J.: Load forecasting using support vector machines: a study on EUNITE competition 2001. IEEE Transactions on Power Systems 19, 1821–1830 (2001)CrossRefGoogle Scholar
  9. 9.
    Reis, A.J.R., Alvis, A.P., da Silva, P.A.: Feature Extraction via Multiresolution Analysis for Short-Term Load Forecasting. IEEE Transactions on Power Systems 20, 189–198 (2005)CrossRefGoogle Scholar
  10. 10.
    Chen, Y., Luh, P.B., Guan, C., Zhao, Y., Michel, L.D., Coolbeth, M.A.: Short-term load forecas-ting: similar day-based wavelet neural network. IEEE Trans. on Power Systems 25, 322–330 (2010)CrossRefGoogle Scholar
  11. 11.
    Australian Energy Market Opeartor (AEMO)
  12. 12.
    Hippert, H.S., Pedreira, C.E., Souza, R.C.: Neural Networks for short-term load forecasting: a review and evaluation. IEEE Transactions on Power Systems 16(1), 44–55 (2001)CrossRefGoogle Scholar
  13. 13.
    Darbellay, G.A., Slama, M.: Forecasting the short-term demand for electricity - Do neural networks stand a better chance? International Journal of Forecasting 16, 71–83 (2000)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Irena Koprinska
    • 1
  • Mashud Rana
    • 1
  • Vassilios G. Agelidis
    • 2
  1. 1.School of Information TechnologiesUniversity of SydneySydneyAustralia
  2. 2.Australian Energy Research InstituteUniversity of New South WalesSydneyAustralia

Personalised recommendations