Advertisement

Abstract

In this work we present a practice-oriented approach for generating load profiles as a means to forecast energy demand by using smart metering time series. The general idea is to apply fuzzy clustering on historic consumption time series. The segmentation yielded helps electricity companies to identify customers with similar consumption behavior. This knowledge can be used to plan available energy capacities in advance. What makes this approach special is that this approach segments consumption time series by time in addition to identifying customer groups. This is done not only to accommodate for customers potentially behaving completely different on working days than on local holidays for example, but also to build the resulting load profiles in a way the electricity companies can adapt with minimal adjustments. We also evaluate our approach using two real world smart metering datasets and discuss potential improvements.

Keywords

Big data Data mining Knowledge discovery Clustering Time series Smart metering Load profiles 

References

  1. 1.
    BTU EVU Beratung GmbH. http://www.btu-evu.de
  2. 2.
    Andersen, F., Larsen, H., Boomsma, T.: Long-term forecasting of hourly electricity load: identification of consumption profiles and segmentation of customers. Energ. Convers. Manag. 68, 244–252 (2013)CrossRefGoogle Scholar
  3. 3.
    Beckel, C., Sadamori, L., et al.: Revealing household characteristics from smart meter data. Energy 78, 397–410 (2014)CrossRefGoogle Scholar
  4. 4.
    Benítez, I., Quijano, A., et al.: Dynamic clustering segmentation applied to load profiles of energy consumption from Spanish customers. Int. J. Electr. Power Energ. Syst. 55, 437–448 (2014)CrossRefGoogle Scholar
  5. 5.
    Bezdek, J.C.: Pattern Recognition with Fuzzy Objective Function Algorithms. Springer, New York (1981)CrossRefzbMATHGoogle Scholar
  6. 6.
    Bock, C.: Clustering-Ansatz zur Erstellung von Lastprofilen zur Vorhersage des Stromverbrauchs. In: Proceedings of the 28th GI-Workshop Grundlagen von Datenbanken (GvDB 2016), pp. 21–26 (2016)Google Scholar
  7. 7.
    Bouguessa, M., Wang, S., Sun, H.: An objective approach to cluster validation. Pattern Recogn. Lett. 27(13), 1419–1430 (2006)CrossRefGoogle Scholar
  8. 8.
    CER – The Commission for Energy Regulation. Accessed via the Irish social science data archive. http://www.ucd.ie/issda
  9. 9.
    Chicco, G., Ilie, I.S.: Support vector clustering of electrical load pattern data. IEEE Trans. Power Syst. 24(3), 1619–1628 (2009)CrossRefGoogle Scholar
  10. 10.
    Diamantoulakis, P.D., Kapinas, V.M., Karagiannidis, G.K.: Big data analytics for dynamic energy management in smart grids (2015). CoRR, abs/1504.02424Google Scholar
  11. 11.
    Figueiredo, V., Rodrigues, F., et al.: An electric energy consumer characterization framework based on data mining techniques. IEEE Trans. Power Syst. 20(2), 596–602 (2005)CrossRefGoogle Scholar
  12. 12.
    Fusco, F., Wurst, M., Yoon, J.: Mining residential household information from low-resolution smart meter data. In: 2012 21st International Conference on Pattern Recognition (ICPR), pp. 3545–3548, November 2012Google Scholar
  13. 13.
    Gath, I., Geva, A.: Unsupervised optimal fuzzy clustering. IEEE Trans. Pattern Anal. Mach. Intell. 11, 773–780 (1989)CrossRefzbMATHGoogle Scholar
  14. 14.
    Hathaway, R.J., Bezdek, J.C.: Fuzzy c-means clustering of incomplete data. IEEE Trans. Syst. Man Cybern. Part B Cybern. 31–35, 735–744 (2001). IEEEGoogle Scholar
  15. 15.
    Hayn, M., et al.: Electricity load profiles in Europe: the importance of household segmentation. Energ. Res. Soc. Sci. 3, 30–45 (2014)CrossRefGoogle Scholar
  16. 16.
    Hernández, L., Baladrón, C., et al.: Classification and clustering of electricity demand patterns in industrial parks. Energies 5(12), 5215 (2012)CrossRefGoogle Scholar
  17. 17.
    Himmelspach, L.: Fuzzy clustering of incomplete data. Ph.D. thesis, Heinrich-Heine-University, Institute of Computer Science (2016)Google Scholar
  18. 18.
    Kolo, A., Kretschmann, C.: Hebung finanzieller Potentiale in der Strombilanzierung. et – Energiewirtschaftliche Tagesfragen 7, 43–45 (2015)Google Scholar
  19. 19.
    Yang, S.L., Shen, C., et al.: A review of electric load classification in smart grid environment. Renew. Sustain. Energ. Rev. 24, 103–110 (2013)Google Scholar
  20. 20.
    López, J.J., Aguado, J.A., et al.: Hopfield-k-means clustering algorithm: a proposal for the segmentation of electricity customers. Electr. Power Syst. Res. 81(2), 716–724 (2011)CrossRefGoogle Scholar
  21. 21.
    Mahmoudi-Kohan, N., Moghaddam, M.P., Sheikh-El-Eslami, M.: An annual framework for clustering-based pricing for an electricity retailer. Electr. Power Syst. Res. 80(9), 1042–1048 (2010)CrossRefGoogle Scholar
  22. 22.
    Misiti, M., Misiti, Y., et al.: Optimized clusters for disaggregated electricity load forecasting. Revstat 8(2), 105–124 (2010)MathSciNetzbMATHGoogle Scholar
  23. 23.
    Rodrigues, F., Duarte, J., et al.: Proceedings of Machine Learning and Data Mining in Pattern Recognition: Third International Conference, MLDM 2003, Leipzig, Germany, 5–7 July 2003, pp. 73–85. Springer (2003)Google Scholar
  24. 24.
    Rudin, C., Waltz, D., et al.: Machine learning for the New York city power grid. IEEE Trans. Pattern Anal. Mach. Intell. 34(2), 328–345 (2012)CrossRefGoogle Scholar
  25. 25.
    Räsänen, T., Voukantsis, D., et al.: Data-based method for creating electricity use load profiles using large amount of customer-specific hourly measured electricity use data. Appl. Energ. 87(11), 3538–3545 (2010)CrossRefGoogle Scholar
  26. 26.
    Schäfer, H., et al.: Analysing the segmentation of energy consumers using mixed fuzzy clustering. In: Fuzzy Systems (FUZZ-IEEE), pp. 1–7, August 2015Google Scholar
  27. 27.
    Viegas, J.P.L., Vieira, S.M., Sousa, J.M.C.: Fuzzy clustering and prediction of electricity demand based on household characteristics. In: 2015 Conference on International Fuzzy Systems Association and European Society Fuzzy Logic and Technolgy (IFSA-EUSFLAT-15)Google Scholar
  28. 28.
    von Roon, D.-I.S., et al.: Statusbericht zum Standardlastprofilverfahren Gas, 11 2014. https://www.ffegmbh.de/kompetenzen/system-markt-analysen/508-statusbericht-standardlastprofile-gas
  29. 29.
    Zhang, X., Sun, C.: Dynamic intelligent cleaning model of dirty electric load data. Energ. Conver. Manag. 49(4), 564–569 (2008)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  1. 1.Institute of Computer ScienceHeinrich-Heine-UniversityDüsseldorfGermany
  2. 2.BTU EVU Beratung GmbHDüsseldorfGermany

Personalised recommendations