Data-driven exploratory models of an electric distribution network for fault prediction and diagnosis

  • 23 Accesses


Data-driven models are becoming of fundamental importance in electric distribution networks to enable predictive maintenance, to perform effective diagnosis and to reduce related expenditures, with the final goal of improving the electric service efficiency and reliability to the benefit of both the citizens and the grid operators themselves. This paper considers a dataset collected over 6 years in a real-world medium-voltage distribution network by the Supervisory Control And Data Acquisition (SCADA) system. A transparent, exploratory, and exhaustive data-mining workflow, based on data characterisation, time-windowing, association rule mining, and associative classification is proposed and experimentally evaluated to automatically identify correlations and build a prognostic–diagnostic model from the SCADA events occurring before and after specific service interruptions, i.e., network faults. Our results, evaluated by both data-driven quality metrics and domain expert interpretations, highlight the capability to assess the limited predictive capability of the SCADA events for medium-voltage distribution networks, while their effective exploitation for diagnostic purposes is promising.

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

Access options

Buy single article

Instant unlimited access to the full article PDF.

US$ 39.95

Price includes VAT for USA

Subscribe to journal

Immediate online access to all issues from 2019. Subscription will auto renew annually.

US$ 99

This is the net price. Taxes to be calculated in checkout.

Fig. 1
Fig. 2
Fig. 3


  1. 1.

    Andresen CA, Torsaeter BN, Haugdal H, Uhlen K (2018) Fault detection and prediction in smart grids. In: IEEE 9th international workshop on applied measurements for power systems (AMPS), pp 1–6

  2. 2.

    Zhang Y, Huang T, Bompard EF (2018) Big data analytics in smart grids: a review. Energy Inf 1(1):8

  3. 3.

    Chunming T, He X, Shuai Z, Jiang F (2017) Big data issues in smart grid a review. Renew Sustain Energy Rev 79:1099–1107

  4. 4.

    Jian W (2016) Early warning method for transmission line galloping based on SVM and adaboost bi-level classifiers. IET Gener Transm Distrib 10(8):3499–3507

  5. 5.

    Zhang Y, Xu Y, Dong ZY, Xu Z, Wong KP (2017) Intelligent early warning of power system dynamic insecurity risk: toward optimal accuracy-earliness tradeoff. IEEE Trans Ind Inf 13(5):2544–2554

  6. 6.

    Cui Q, El-Arroudi K, Joos G (2017) An effective feature extraction method in pattern recognition based high impedance fault detection. In: 19th International conference on intelligent system application to power systems (ISAP), pp 1–6

  7. 7.

    Jiang H, Dai X, Gao W, Zhang J, Zhang Y, Muljadi E (2016) Spatial-temporal synchrophasor data characterization and analytics in smart grid fault detection, identification and impact causal analysis. IEEE Trans Smart Grid 7(09):1–1

  8. 8.

    De Santis E, Livi L, Sadeghian A, Rizzi A (2015) Modeling and recognition of smart grid faults by a combined approach of dissimilarity learning and one-class classification. Neurocomputing 170(C):368–383

  9. 9.

    Cai Y, Chow M (2009) Exploratory analysis of massive data for distribution fault diagnosis in smart grids. In: IEEE power energy society general meeting, pp 1–6

  10. 10.

    De Santis E, Rizzi A, Sadeghian A (2017) A learning intelligent system for classification and characterization of localized faults in smart grids. IEEE congress on evolutionary computation (CEC). Donostia, San Sebastián, 5–8 June 2017, pp 2669–2676

  11. 11.

    Zhao R, Iqbal MRA, Bennett KP, Ji Q (2016) Wind turbine fault prediction using soft label SVM. In: 2016 23rd International conference on pattern recognition (ICPR), pp 3192–3197

  12. 12.

    FajarHazrat S, Khatri P, Ahmed BM, Zama M (2018) Grid monitoring using solar SCADA dataset. IOSR J Electr Electron Eng 13(5):39–48

  13. 13.

    Bartolini N, Scappaticci L, Garinei A, Becchetti M, Terzi L (2017) Analysing wind turbine states and SCADA Data for fault diagnosis. Int J Renew Energy Res 7(1):323–329

  14. 14.

    Castellani F, Astolfi D, Terzi L (2016) Analyzing state dynamics of wind turbines through SCADA data mining, vol 4. Springer, Cham, pp 213–223

  15. 15.

    Li B, Zhang WG, Ning DF, Yin W (2007) Fault prediction system based on neural network model, vol 10, pp 496 – 496

  16. 16.

    Liu J, Geng G (2015) Fault prediction for power plant equipment based on support vector regression. In: 8th International symposium on computational intelligence and design (ISCID), vol 2, pp 461–464

  17. 17.

    Han R, Zhou Q (2016) Data-driven solutions for power system fault analysis and novelty detection. In: 11th International conference on computer science education (ICCSE), pp 86–91

  18. 18.

    Liu D, Wu B, Gu C, Ma Y, Wang B (2017) A multidimensional time-series association rules algorithm based on spark. In: 13th International conference on natural computation, fuzzy systems and knowledge discovery (ICNC-FSKD), pp 1946–1952

  19. 19.

    Qiu F-X , Si F, Xu Z-G (2009) Association rules mining based on principal component analysis and sensor fault detection of power plant. In: Proceedings of the CSEE, vol 5, pp 97–102

  20. 20.

    Wang X, McArthur S, Strachan S, Kirkwood JD, Paisley B (2017) A data analytic approach to automatic fault diagnosis and prognosis for distribution automation. IEEE Trans Smart Grid 05:1–1

  21. 21.

    Nisi M, Renga D, Apiletti D, Giordano D, Huang T, Zhang Y, Mellia M, Baralis E (2019). Transparently mining data from a medium-voltage distribution network: a prognostic–diagnostic analysis. In: Proceedings of the Workshops of the EDBT/ICDT 2019 joint conference, EDBT/ICDT 2019, Lisbon, 26 Mar 2019

  22. 22.

    Pang-Ning T, Michael S, Vipin K (2005) Introduction to data mining. Addison-Wesley, Boston

  23. 23.

    Liu B, Hsu W, Ma Y, Liu B, Hsu Y (1998) Integrating classification and association rule mining. In: Proceedings of the fourth international conference on knowledge discovery and data mining, pp 24–25

  24. 24.

    Baralis E, Chiusano S, Garza P (2008) A lazy approach to associative classification. IEEE Trans Knowl Data Eng 20(2):156–171

  25. 25.

    Genuer R, Poggi JM, Tuleau C (2008) Random forests: some methodological insights. Technical report, INRIA

  26. 26.

    Pedregosa F, Varoquaux G, Gramfort A (2011) Scikit-learn: machine learning in Python. J Mach Learn Res 12:2825–2830

Download references


This work has been partially funded by Enel Italia, e-distribuzione, and the SmartData@PoliTO center for Data Science technologies and applications. We are grateful to Paolo Garza and Giuseppe Attanasio for their help in exploiting the L3 associative classifier.

Author information

Correspondence to Daniela Renga.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Renga, D., Apiletti, D., Giordano, D. et al. Data-driven exploratory models of an electric distribution network for fault prediction and diagnosis. Computing (2020).

Download citation


  • Smart grid
  • Predictive maintenance
  • Fault diagnosis
  • Medium Voltage distribution networks
  • Data mining
  • Associative classification

Mathematics Subject Classification

  • 68T04