IDEAS home Printed from https://ideas.repec.org/a/gam/jmathe/v13y2025i2p316-d1570484.html
   My bibliography  Save this article

Bulk Low-Inertia Power Systems Adaptive Fault Type Classification Method Based on Machine Learning and Phasor Measurement Units Data

Author

Listed:
  • Mihail Senyuk

    (Department of Automated Electrical Systems, Ural Federal University, 620002 Yekaterinburg, Russia)

  • Svetlana Beryozkina

    (College of Engineering and Technology, American University of the Middle East, Kuwait)

  • Inga Zicmane

    (Faculty of Electrical and Environmental Engineering, Institute of Industrial Electronics, Electrical Engineering and Energy, Riga Technical University, Azenes Street 12/1, LV-1048 Riga, Latvia)

  • Murodbek Safaraliev

    (Department of Automated Electrical Systems, Ural Federal University, 620002 Yekaterinburg, Russia)

  • Viktor Klassen

    (Department of Automated Electrical Systems, Ural Federal University, 620002 Yekaterinburg, Russia)

  • Firuz Kamalov

    (Department of Electrical Engineering, Canadian University Dubai, Dubai 117781, United Arab Emirates)

Abstract

This research focuses on developing and testing a method for classifying disturbances in power systems using machine learning algorithms and phasor measurement unit (PMU) data. To enhance the speed and accuracy of disturbance classification, we employ a range of ensemble machine learning techniques, including Random forest, AdaBoost, Extreme gradient boosting (XGBoost), and LightGBM. The classification method was evaluated using both synthetic data, generated from transient simulations of the IEEE24 test system, and real-world data from actual transient events in power systems. Among the algorithms tested, XGBoost achieved the highest classification accuracy, with 96.8% for synthetic data and 85.2% for physical data. Additionally, this study investigates the impact of data sampling frequency and calculation window size on classification performance. Through numerical experiments, we found that increasing the signal sampling rate beyond 5 kHz and extending the calculation window beyond 5 ms did not significantly improve classification accuracy.

Suggested Citation

  • Mihail Senyuk & Svetlana Beryozkina & Inga Zicmane & Murodbek Safaraliev & Viktor Klassen & Firuz Kamalov, 2025. "Bulk Low-Inertia Power Systems Adaptive Fault Type Classification Method Based on Machine Learning and Phasor Measurement Units Data," Mathematics, MDPI, vol. 13(2), pages 1-26, January.
    • Handle: RePEc:gam:jmathe:v:13:y:2025:i:2:p:316-:d:1570484
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2227-7390/13/2/316/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/2227-7390/13/2/316/
    Download Restriction: no
    ---><---

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jmathe:v:13:y:2025:i:2:p:316-:d:1570484. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    We have no bibliographic references for this item. You can help adding them by using this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.