Phase preserving profile generation from measurement data by clustering and performance analysis: a tool for network planning and operation


The need for improved operational efficiency planning accuracy leads to a growing number of sensors and other monitoring sources in our power system. New methods for properly dealing with this increasing amount of data are required. This paper presents how clustering can help to drastically reduce the processing time of energy data time series. The developed approach categorizes similar load behavior by means of agglomerative hierarchical clustering based on their correlation coefficient. It includes the determination of the best number of clusters to model different load patterns with respect to the total error given as a key performance indicator. The results are a reduced set of representative three phase load profiles based on the data input and clustering configurations. The accuracy of these representative profiles is validated by resembling the original data set. Dependent on available computational resources a network operator can use this to intelligently compress measurement data while keeping the required accuracy. The method is demonstrated on data from the testbed of Aspern Smart City Research in Seestadt Aspern, Austria.

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

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16


  1. 1.

    Synthetic load profiles: APCS—power clearing & settlement.

  2. 2.

    Aggarwal CC (2015) Cluster analysis. In: Data mining. Springer, Cham, pp 153–204. doi:10.1007/978-3-319-14142-8

  3. 3.

    Ahmadi H, Mart JR, von Meier A (2016) A linear power flow formulation for three-phase distribution systems. IEEE Trans Power Syst 31(6):5012–5021. doi:10.1109/TPWRS.2016.2533540

    Article  Google Scholar 

  4. 4.

    Al-Wakeel A, Wu J (2016) K-means based cluster analysis of residential smart meter measurements. Energy Procedia 88:754–760. doi:10.1016/j.egypro.2016.06.066

    Article  Google Scholar 

  5. 5.

    Al-Wakeel A, Wu J, Jenkins N (2016) K-means based load estimation of domestic smart meter measurements. Appl Energy. doi:10.1016/j.apenergy.2016.06.046

    Google Scholar 

  6. 6.

    Anuar N, Zakaria Z (2011) Determination of fuzziness parameter in load profiling via fuzzy c-means. In: 2011 IEEE control and system graduate research colloquium, pp 139–142. doi:10.1109/ICSGRC.2011.5991846

  7. 7.

    Birch AP, Ozveren CS, Sapeluk AT (1996) A generic load profiling technique using fuzzy classification. In: Eighth international conference on metering and tariffs for energy supply (Conf. Publ. No. 426), pp 203–207. doi:10.1049/cp:19960507

  8. 8.

    Bletterie B, Kadam S, Pitz R, Abart A (2013) Optimisation of LV networks with high photovoltaic penetration—balancing the grid with smart meters. In: 2013 IEEE Grenoble Conference, pp 1–6. doi:10.1109/PTC.2013.6652366

  9. 9.

    Cartina G, Grigoras G, Bobric EC, Comanescu D (2009) Improved fuzzy load models by clustering techniques in optimal planning of distribution networks. In: 2009 IEEE Bucharest PowerTech, pp 1–6. doi:10.1109/PTC.2009.5282025

  10. 10.

    Gerbec D, Gasperic S, Smon I, Gubina F (2004) Determining the load profiles of consumers based on fuzzy logic and probability neural networks. IEE Proc Gener Transm Distrib 151(3):395–400. doi:10.1049/ip-gtd:20040472

    Article  Google Scholar 

  11. 11.

    Gerbec D, Gasperic S, Smon I, Gubina F (2002) A methodology to classify distribution load profiles. In: IEEE/PES transmission and distribution conference and exhibition, vol 2, pp 848–851. doi:10.1109/TDC.2002.1177586

  12. 12.

    Mutanen A, Ruska M, Repo S, Jarventausta P (2011) Customer classification and load profiling method for distribution systems. IEEE Trans Power Deliv 26(3):1755–1763. doi:10.1109/TPWRD.2011.2142198

    Article  Google Scholar 

  13. 13.

    Nazarko J, Styczynski ZA (1999) Application of statistical and neural approaches to the daily load profiles modelling in power distribution systems. In: 1999 IEEE transmission and distribution conference (Cat. No. 99CH36333), vol 1, pp 320–325. doi:10.1109/TDC.1999.755372

  14. 14.

    Ozveren CS, Vechakanjana C, Birch AP (2002) Fuzzy classification of electrical load demand profiles-a case study. In: 2002 fifth international conference on power system management and control Conf. Publ. No. 488), pp 353–358. doi:10.1049/cp:20020061

  15. 15.

    Pitt BD, Kitschen DS (1999) Application of data mining techniques to load profiling. In: Proceedings of the 21st international conference on power industry computer applications. Connecting Utilities. PICA 99. To the Millennium and Beyond (Cat. No.99CH36351), pp 131–136. doi:10.1109/PICA.1999.779395

  16. 16.

    Prahastono I, King D, Ozveren CS (2007) A review of electricity load profile classification methods. In: 2007 42nd international universities power engineering conference, pp 1187–1191. doi:10.1109/UPEC.2007.4469120

  17. 17.

    Prahastono I, King DJ, Ozveren CS, Bradley D (2008) Electricity load profile classification using fuzzy c-means method. In: 2008 43rd international universities power engineering conference, pp 1–5. doi:10.1109/UPEC.2008.4651527

  18. 18.

    Zakaria Z, Lo KL (2009) Two-stage fuzzy clustering approach for load profiling. In: 2009 44th international universities power engineering conference (UPEC), pp 1–5

  19. 19.

    Zalewski W (2006) Application of fuzzy inference to electric load clustering. In: 2006 IEEE power India conference, p 5. doi:10.1109/POWERI.2006.1632594

Download references


This was work was conducted within the research projects ISOLVES: iNIS - integrated Network Information System funded within the program IKT der Zukunft by the Austrian Klima- und Energiefonds) and supported by data of the smart grid testbed of the Aspern Smart City Research.

Author information



Corresponding author

Correspondence to Paul Zehetbauer.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Zehetbauer, P., Stifter, M. & Rao, B.V. Phase preserving profile generation from measurement data by clustering and performance analysis: a tool for network planning and operation. Comput Sci Res Dev 33, 145–155 (2018).

Download citation


  • Load measurements
  • Time series analysis
  • Clustering
  • Synthetic profiles