Hybrid Models for Short-Term Load Forecasting Using Clustering and Time Series

  • Wael AlkhatibEmail author
  • Alaa AlhamoudEmail author
  • Doreen Böhnstedt
  • Ralf Steinmetz
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10306)


Short-term forecasting models on the micro-grid level help guaranteeing the cost-effective dispatch of available resources and maintaining shortfalls and surpluses to a minimum in the spot market. In this paper, we introduce two time series models for forecasting the day-ahead total power consumption and the fine-granular 24-hour consumption pattern of individual buildings. The proposed model for predicting the consumption pattern outperforms the state-of-the-art algorithm of Pattern Sequence-based Forecasting (PSF). Our analysis reveals that the clustering of individual buildings based on their seasonal, weekly, and daily patterns of power consumption improves the prediction accuracy and increases the time efficiency by reducing the search space.


Smart grid Sequence-based forecasting Time series models K-means Hierarchical clustering 


  1. 1.
    Alfares, H.K., Nazeeruddin, M.: Electric load forecasting: literature survey and classification of methods. Int. J. Syst. Sci. 33(1), 23–34 (2002)CrossRefzbMATHGoogle Scholar
  2. 2.
    Aman, S., Frincu, M., Chelmis, C., Noor, M.U.: Empirical comparison of prediction methods for electricity consumption forecasting. Department of Computer Science, University of Southern California, Los Angeles, CA, 90089 (2012)Google Scholar
  3. 3.
    Commission for Energy Regulation (CER): Electricity smart metering technology trials findings report. ESB Networks, Belgard Square North, Tallaght, Dublin 24 (2011)Google Scholar
  4. 4.
    Fan, S., Hyndman, R.: Short-term load forecasting based on a semi-parametric additive model. IEEE Trans. Power Syst. 27(1), 134–141 (2012)CrossRefGoogle Scholar
  5. 5.
    Gabriel, S.: An electricity market for germany’s energy transition. Federal Ministry for Economic Affairs and Energy (BMWi), PRpetuum GmbH, Munchen (2014)Google Scholar
  6. 6.
    Hong, T., Gui, M., Baran, M., Willis, H.: Modeling and forecasting hourly electric load by multiple linear regression with interactions. In: Power and Energy Society General Meeting 2010, pp. 1–8. IEEE, July 2010Google Scholar
  7. 7.
    Jiang, H., Lee, Y., Liu, F.: Anomaly detection, forecasting and root cause analysis of energy consumption for a portfolio of buildings using multi-step statistical modeling, US Patent App. 13/098,044 (2012)Google Scholar
  8. 8.
    Coughlin, K., Piette, M.A.C.G., Kiliccote, S: Emergency demand response program manual, Sect. 5.2: calculation of customer baseline load (CBL). New York Independent System Operator, Southern California Edison, Technical report (2010)Google Scholar
  9. 9.
    Coughlin, K., Piette, M.A.C.G., Kiliccote, S: 10-day average baseline and day-of adjustment. Southern California Edison, Technical report (2011)Google Scholar
  10. 10.
    Metaxiotis, K., Kagiannas, A.D.A., Psarras, J.: Artificial intelligence in short-term electric load forecasting: a state-of-the-art survey for the researcher. Energy Convers. Manage. 44, 1525–1534 (2003)CrossRefGoogle Scholar
  11. 11.
    Khotanzad, A., Afkhami-Rohani, R., Lu, T.L., Abaye, A., Davis, M., Maratukulam, D.: Annstlf-a neural-network-based electric load forecasting system. IEEE Trans. Neural Netw. 8(4), 835–846 (1997)CrossRefGoogle Scholar
  12. 12.
    Martinez Alvarez, F., Troncoso, A., Riquelme, J., Aguilar Ruiz, J.: Energy time series forecasting based on pattern sequence similarity. IEEE Trans. Knowl. Data Eng. 23(8), 1230–1243 (2011)CrossRefGoogle Scholar
  13. 13.
    Rui, Y., El-Keib, A.: A review of ann-based short-term load forecasting models. In: Proceedings of the Twenty-Seventh Southeastern Symposium on System Theory 1995, pp. 78–82 (1995)Google Scholar
  14. 14.
    Shen, W., Babushkin, V., Aung, Z., Woon, W.: An ensemble model for day-ahead electricity demand time series forecasting. In: Proceedings of the Fourth International Conference on Future Energy Systems, pp. 51–62. ACM, New York (2013)Google Scholar
  15. 15.
    Silipo, R., Winters, P.: Big data, smart energy, and predictive analytics time series prediction of smart energy data (2013).
  16. 16.
    Simmhan, Y., Noor, M.: Scalable prediction of energy consumption using incremental time series slustering. In: 2013 IEEE International Conference on Big Data, pp. 29–36, October 2013Google Scholar
  17. 17.
    Wan, S., Yu, X.-H.: Facility power usage modeling and short term prediction with artificial neural networks. In: Zhang, L., Lu, B.-L., Kwok, J. (eds.) ISNN 2010. LNCS, vol. 6064, pp. 548–555. Springer, Heidelberg (2010). doi: 10.1007/978-3-642-13318-3_68 CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Fachgebiet Multimedia KommunikationTechnische Universität DarmstadtDarmstadtGermany

Personalised recommendations