Short-term prediction of power outages in electrical distribution networks

• Autorzy: Makungo Pfanelo , Hlalele Tlotlollo , Sumbwanyambe Mbuyu

Identyfikatory

DOI

10.24425/aee.2024.152113

• Języki publikacji: EN

Abstrakty

EN

Predictive maintenance and reliability engineering are critical in industrial settings to enhance equipment performance and minimize unplanned downtime. This research, conducted within the machine learning framework, presents innovative solutions to the challenging problem of equipment failure prediction. The study creatively utilizes extensive datasets, including equipment records, weather conditions, and maintenance logs, to develop robust predictive models. Two distinct machine learning models are established for equipment and cables/lines, addressing the intricacies of class imbalances and missing data attributes. Model refinement, feature engineering, and interdisciplinary collaboration enhance predictive accuracy, precision, and recall. Notably, this research highlights the creative application of engineering knowledge and data science techniques, reasoning about complex equipment systems, and the importance of problem decomposition. The outcomes underscore the potential for real-time predictive maintenance in industrial contexts, offering substantial cost savings and improved equipment reliability. This research contributes to the evolving field of predictive maintenance and paves the way for future innovations in reliability engineering.

Słowa kluczowe

EN

data preprocessing; load-shedding; machine learning; outage prediction; predictive maintenance; predictive model

• Wydawca: Polish Academy of Sciences, Committee on Electrical Engineering
• Czasopismo: Archives of Electrical Engineering
• Rocznik: 2024
• Tom: Vol. 73, nr 4
• Strony: 1103--1121
• Opis fizyczny: Bibliogr. 13 poz., tab., wykr., wz.

Twórcy

autor

Makungo Pfanelo

• University of South Africa, Department of Electrical and Smart Systems Engineering, Johannesburg, South Africa
• [e-mail]

• https://orcid.org/0009-0009-7232-3750

autor

Hlalele Tlotlollo

• [e-mail]
• University of South Africa, Department of Electrical and Smart Systems Engineering, Johannesburg, South Africa

• https://orcid.org/0000-0003-0550-9597

autor

Sumbwanyambe Mbuyu

• University of South Africa, Department of Electrical and Smart Systems Engineering, Johannesburg, South Africa

• https://orcid.org/0000-0003-1709-0607

Bibliografia

• [1] Asaridis P., Molinari D., Ballio F., A conceptual model for the estimation of flood damage to power grids (2021), DOI: 10.5194/egusphere-egu21-2721.
• [2] Nduhuura P., Garschagen M., Zerga A., Impacts of Electricity Outages in Urban Households in Developing Countries: A Case of Accra, Ghana, Energies, vol. 14, no. 12, 3676 (2021), DOI: 10.3390/en14123676.
• [3] Onaolapo A., Carpanen R., Dorrell D., Ojo E., A comparative assessment of conventional and artificial neural networks methods for electricity outage forecasting, Energies, vol. 15, no. 2, 511 (2022), DOI: 10.3390/en15020511.
• [4] O’Fallon C., Gopstein A., Quantifying operational resilience benefits of the smart grid (2021), DOI: 10.6028/nist.tn.2137.
• [5] Kiran D., Failure Modes and Effects Analysis. Total Quality Management, pp. 373–389 (2017), DOI: 10.1016/B978-0-12-811035-5.00026-X.
• [6] Tsioumpri E., Stephen B., McArthur S., Weather Related Fault Prediction in Minimally Monitored Distribution Networks, Energies, vol. 14, no. 8, 2053 (2021), DOI: 10.3390/en14082053.
• [7] Fakih A., Ghazalian P., Ghazzawi N., The Effects of Power Outages on the Performance of Manufacturing Firms in the Mena Region, Review of Middle East Economics and Finance, vol. 16, no. 3 (2020), DOI: 10.1515/rmeef-2020-0011.
• [8] Luo G., Huang F., Yang Y., Zhang B., Chen Z., Peng W., Intelligent aided decision-making method for power grid outage maintenance plan based on machine learning (2023), DOI: 10.1117/12.2686169.
• [9] Service E.A., Eskom, March 2020 [online], accessed December 2023.
• [10] Evans J., Daily Maverick, 27 June 2022, available at: https://www.dailymaverick.co.za/article/2022-06- 27-pushing-the-limits-why-load-shedding-puts-even-more-pressure-on-an-ageing-electrical-system/, accessed 12 March 2023.
• [11] Berk A., Dynamic Modeling of Power Outages Caused by Thunderstorms (2020), DOI: 10.3390/forecast2020008.
• [12] Godemel F., Powermag, Power, 11 November 2022 [online], available at: https://www.powermag.com/ blog/power-outages-due-to-extreme-weather-must-become-a-thing-of-the-past/, accessed 12 March 2023.
• [13] Géron A., Hands-on Machine Learning with Scikit-Learn, Keras, and TensorFlow, United States of America, O’Reilly Media, ISBN: 9781492032649 (2019).