Skip to main content
SpringerLink
Log in

Load forecasting through functional clustering and ensemble learning

  • Regular Paper
  • Published:
Knowledge and Information Systems Aims and scope Submit manuscript

Abstract

In this paper a load forecasting methodology for 2 days-ahead based on functional clustering and on ensemble learning is presented. Due to the longitudinal nature of the load diagrams, these are segmented using a functional clustering procedure to group together similar daily load curves concerning its phase and amplitude. Next, ensemble learning of extreme learning machine models, developed for several load curves groups, is made to fully integrate the advantages of all models and improve the accuracy of the final load forecasting. The quality of this methodology is illustrated with a real case study concerning load consumption patterns of clients with different economic activities from a Portuguese energy trading company. The forecasting results for 2 days-ahead are good for practical use, yielding a \(R^{2} = 0.967\).

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

References

  1. Feinberg EA, Genethliou D (2005) Load forecasting. In: Applied mathematics for restructured electric power systems. Springer, pp 269–285

  2. Suganthi L, Samuel AA (2012) Energy models for demand forecasting a review. Renew Sustain Energy Rev 16(2):1223–1240

    Article  Google Scholar 

  3. Alfares HK, Nazeeruddin M (2002) Electric load forecasting: literature survey and classification of methods. Int J Syst Sci 33(1):23–34

    Article  MATH  Google Scholar 

  4. Metaxiotis K, Kagiannas A, Askounis D, Psarras J (2003) Artificial intelligence in short term electric load forecasting: a state-of-the-art survey for the researcher. Energy Convers Manag 44(9):1525–1534

    Article  Google Scholar 

  5. Badar-Ul-Islam E, Qureshi SA (2011) Comparison of conventional and modern load forecasting techniques based on artificial intelligence and expert systems. Int J Comput Sci 8(5):28–37

    Google Scholar 

  6. Liao TW (2005) Clustering of time series data a survey. Pattern Recognit 38(11):1857–1874

    Article  MATH  Google Scholar 

  7. Jacques J, Preda C (2014) Functional data clustering: a survey. Adv Data Anal Classif 8(3):231–255

    Article  MathSciNet  Google Scholar 

  8. Goia A, May C, Fusai G (2010) Functional clustering and linear regression for peak load forecasting. Int J Forecast 26(4):700–711

    Article  Google Scholar 

  9. Antoch J, Prchal L, de Rosa MR, Sarda P (2008) Functional linear regression with functional response: application to prediction of electricity consumption. In: Functional and operatorial statistics. Springer, pp 23–29

  10. Cheng Q, Yao J, Wu H, Chen S, Liu C, Yao P (2013) Short-term load forecasting with weather component based on improved extreme learning machine. In: Chinese Automation Congress (CAC). IEEE, pp 316–321

  11. Matijaš M, Suykens JA, Krajcar S (2013) Load forecasting using a multivariate meta-learning system. Expert Syst Appl 40(11):4427–4437

    Article  Google Scholar 

  12. Kaur A, Pedro HT, Coimbra CF (2014) Ensemble re-forecasting methods for enhanced power load prediction. Energy Convers Manag 80:582–590

    Article  Google Scholar 

  13. Slaets L, Claeskens G, Hubert M (2012) Phase and amplitude-based clustering for functional data. Comput Stat Data Anal 56(7):2360–2374

    Article  MathSciNet  MATH  Google Scholar 

  14. Genolini C, Falissard B (2010) KmL: k-means for longitudinal data. Comput Stat 25(2):317–328

    Article  MathSciNet  MATH  Google Scholar 

  15. Caliński T, Harabasz J (1974) A dendrite method for cluster analysis. Commun Stat Theory Methods 3(1):1–27

    Article  MathSciNet  MATH  Google Scholar 

  16. Ray S, Turi RH (1999) Determination of number of clusters in k-means clustering and application in colour image segmentation. In: Proceedings of the 4th international conference on advances in pattern recognition and digital techniques, Calcutta, India, pp 137–143

  17. Davies DL, Bouldin DW (1979) A cluster separation measure. IEEE Trans Pattern Anal Mach Intell 2:224–227

    Article  Google Scholar 

  18. Huang G-B, Zhu Q-Y, Siew C-K (2006) Extreme learning machine: theory and applications. Neurocomputing 70(1):489–501

    Article  Google Scholar 

  19. Rao CR, Mitra SK (1971) Generalized inverse of matrices and its applications, vol 7. Wiley, New York

    MATH  Google Scholar 

  20. Bishop CM et al (2006) Pattern recognition and machine learning, vol 4. Springer, New York

    MATH  Google Scholar 

  21. Trindade A (2015) UCI machine learning repository. http://archive.ics.uci.edu/ml/datasets/ElectricityLoadDiagrams20112014

  22. Genolini C, Alacoque X, Sentenac M, Arnaud C (2015) kml and kml3d: R packages to cluster longitudinal data. J Stat Software 65(4):1–34. http://www.jstatsoft.org/v65/i04/

  23. Han J, Kamber M (2006) Data mining: concepts and techniques. Morgan Kaufmann, Burlington

    MATH  Google Scholar 

  24. Taylor JW, Buizza R (2003) Using weather ensemble predictions in electricity demand forecasting. Int J Forecast 19(1):57–70

    Article  Google Scholar 

  25. Fan S, Chen L, Lee W-J (2008) Short-term load forecasting using comprehensive combination based on multi-meteorological information. In: IEEE/IAS industrial and commercial power systems technical conference. IEEE, pp 1–7

  26. Taylor JW, Buizza R (2002) Neural network load forecasting with weather ensemble predictions. IEEE Trans Power Syst 17(3):626–632

    Article  Google Scholar 

  27. López M, Valero S, Senabre C, Aparicio J, Gabaldón A (2011) Development of a model for short-term load forecasting with neural networks and its application to the electrical Spanish market. In: 8th international conference on the European Energy Market (EEM). IEEE, pp 321–326

  28. Llanos J, Saez D, Palma-Behnke R, Nunez A, Jimenez-Estevez G (2012) Load profile generator and load forecasting for a renewable based microgrid using self organizing maps and neural networks. In: The 2012 international joint conference on neural networks (IJCNN). IEEE, pp 1–8

Download references

Acknowledgements

The authors would like to acknowledge the support by FEDER Funds through the program “Operacional Regional do Norte - Concurso 07/SI/2012” under the project Ferramenta de Gestão para a Aquisição de Electricidade nos Mercados Grossistas OMIP e OMIE (WATTUP-2013-04/2014).

Author information

Authors and Affiliations

  1. Department of Informatics, Institute of Engineering Polytechnic of Porto (ISEP/IPP), Porto, Portugal

    Fátima Rodrigues

  2. Elergone Energia, R. Almeiriga 586, 4450-608, Matosinhos, Portugal

    Artur Trindade

Authors
  1. Fátima Rodrigues
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Artur Trindade
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Fátima Rodrigues.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Rodrigues, F., Trindade, A. Load forecasting through functional clustering and ensemble learning. Knowl Inf Syst 57, 229–244 (2018). https://doi.org/10.1007/s10115-018-1169-y

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10115-018-1169-y

Keywords

Search

Navigation