Clustering Representative Electricity Load Data Using a Particle Swarm Optimization Algorithm

  • Erik CuevasEmail author
  • Emilio Barocio Espejo
  • Arturo Conde Enríquez
Part of the Studies in Computational Intelligence book series (SCI, volume 822)


The increasing deployment of smart meters to collect load profile data in real-time is generating new opportunities for analysing electric power distribution system. Storing, managing and analysing large volumes of collected data, however, is challenging. Measured data is high-dimensional in nature and may contain hidden information and complex patterns that need to be interpreted. In this chapter, a method that combines dimensionality reduction (DR) technique with Particle Swarm Optimization (PSO) algorithm for clustering load profile electricity data is presented. The DR techniques allows to obtain a low-dimensional data model that can be used to project representative electricity load (REL) data onto an easily interpretable 3D space. The PSO algorithm and a validation index algorithm is then applied to obtain an optimal number of clusters. The presented framework methodology is applied to clustering historical REL data. The REL data allows to evaluate the ability of linear and nonlinear DR techniques to extract the relevant information that may be useful to visualize and improve the clustering data process.


  1. 1.
    R. Granell, C.J. Axon, D.C.H. Wallom, Impacts of raw data temporal resolution using selected clustering methods on residential electricity load profiles. IEEE Trans. Power Syst. 30(6), 3217–3224 (2015)CrossRefGoogle Scholar
  2. 2.
    G. Chicco, R. Napoli, P. Postolache, M. Scutriu, C. Toader, Customer characterization options for improving the tariff offer. IEEE Trans. Power Syst. 18(1), 381–387 (2003)CrossRefGoogle Scholar
  3. 3.
    G. Chicco, Overview and performance assessment of the clustering methods for electrical load pattern grouping. Energy 42(1), 68–80 (2012)CrossRefGoogle Scholar
  4. 4.
    A. Morán, J.J. Fuertes, M.A. Prada, S. Alonso, P. Barrientos, I. Díaz, in Analysis of Electricity Consumption Profiles by Means of Dimensionality Reduction Techniques. EANN International Conference on Engineering Applications of Neural Networks, London, UK, pp. 152–161 (2012)CrossRefGoogle Scholar
  5. 5.
    L. Van der Maaten, E. Postman, J. can den Herik, Dimensionality reduction: a comparative review. J. Mach. Learn. Res. 10, 1–41 (2009)Google Scholar
  6. 6.
    G. Chicco, R. Napoli, F. Piglione, Comparisons among clustering techniques for electricity customer classification. IEEE Trans. Power Syst. 21(2), 933–940 (2006)CrossRefGoogle Scholar
  7. 7.
    M. Sun, I. Konstantelosy, G. Strbac, C-Vine copula mixture model for clustering of residential electrical load pattern data. IEEE Trans. Power Syst. 32(3), 2382–2393 (2017)CrossRefGoogle Scholar
  8. 8.
    G. Chicco, O.M. Ionel, R. Porumb, Electrical load pattern grouping based on centroid model with ant colony clustering. IEEE Trans. Power Syst. 28(2), 1706–1715 (2013)CrossRefGoogle Scholar
  9. 9.
    F. Lezama, A. Rodriguez, E. Muñoz de Cote, L. Sucar, in Electrical Load Pattern Shape Clustering Using Ant Colony Optimization. European Conference on the Applications of Evolutionary Computation (Springer, Cham, 2016), pp. 491–506CrossRefGoogle Scholar
  10. 10.
    E.K. Cervera, E. Barocio, F.R. Sevilla Segundo, P. Korba, R.J. Betancourt, Particle swarm intelligence optimization approach for clustering of low and high dimensional databases. Submitted at IEEE general meeting (2019)Google Scholar
  11. 11.
    J. Wu, Advances in K-Means Clustering (Springer theses, China, 2012). H. Ward, Hierarchical grouping to optimize an objective function. J. Am. Stat. Assoc. 58, 236–244 (1963)Google Scholar
  12. 12.
    J.C. Bezdek, Pattern Recognition with Fuzzy Objective Function Algorithm (Plenum, New York, 1981)CrossRefGoogle Scholar
  13. 13.
    Y.H. Pao, D.J. Sobajic, Combines use of unsupervised and supervised learning for dynamic security assessment. IEEE Trans. Power Syst. 7(2), 878–884 (1992)CrossRefGoogle Scholar
  14. 14.
    I.T. Jolliffe, in Springer Series in Statistic, 2nd edn. Principal Component Analysis (New York, 1986), pp. 32–500Google Scholar
  15. 15.
    N.R. Sakthivel, B.B. Nair, M. Elangovan, V. Sugumaran, S. Saravanmurugan, Comparison of dimensionality reduction techniques for the fault diagnosis of mono block centrifugal pump using vibrations signals. Elsevier Eng. Sci. Technol. Int. J. (2014)Google Scholar
  16. 16.
    A. Arechiga, E. Barocio, J. Ayon, H. Garcia, in Comparison of Dimensionality Reduction Techniques for Clustering and Visualization of Load Profiles. IEEE PES T&D-LA, in Proc. (2016)Google Scholar
  17. 17.
    J. Leeuw, W. Heiser, in Theory of Multidimensional Scaling. Handbook of Statistics, vol. 2, pp. 285–316 (1982)Google Scholar
  18. 18.
    E.W. Dijkstra, A note on two problems in conexion with graphs. Numer. Math. 1, 269–271 (1959)MathSciNetCrossRefGoogle Scholar
  19. 19.
    G. Hinton, S. Roweis, in Stochastic Neighbor Embedding. Advances in Neural Information Processing System, vol. 15, MA. pp. 833–840 (2002)Google Scholar
  20. 20.
    L. Wang, T.V.U. Nguyen, J.C. Bezdek, C. Leckie, K. Ramamohanarao, in iVAT and aVAT: Enhanced Visual Analysis for Cluster Tendency Assessment. Proc. PAKDD, Hyderabad, India, June 2010CrossRefGoogle Scholar
  21. 21.
    J.C. Bezdek, R.J. Hathaway, in VAT: a Tool for Visual Assessment of Cluster Tendency. Proceedings of the 2002 International Joint Conference on Neural Networks, Honolulu, HI, pp. 2225–2230 (2002)Google Scholar
  22. 22.
    A. Chatterjee, P. Siarry, Nonlinear inertia weight variation for dynamic adaptation in particle swarm optimizacion. Comput. Oper. Res. 33, 859–871 (2006)CrossRefGoogle Scholar
  23. 23.
    Q. Zhao, P. Fränti, WB-index: a sum-of-squares based index for cluster validity. Data Knowl. Eng. 92, 77–89 (2014)CrossRefGoogle Scholar
  24. 24.

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Erik Cuevas
    • 1
    Email author
  • Emilio Barocio Espejo
    • 2
  • Arturo Conde Enríquez
    • 3
  1. 1.Departamento de Electrónica, CUCEIUniversidad de GuadalajaraGuadalajaraMexico
  2. 2.CUCEIUniversidad de GuadalajaraGuadalajaraMexico
  3. 3.Universidad Autónoma de Nuevo LeónSan Nicolás de los GarzaMexico

Personalised recommendations