Assistant Secretary, SBTE, Department of Science, Technology and Technical
JournalPIJST
Volume / Issue2 / 1
Pages1–12
Published31 Jan 2025
Paper IDPIJST21J25001
Views / Downloads1 / 0
Article summary
Abstract
In this paper, we investigate three traditional SSL techniques for event detection: self-training, transductive support vector machines (TSVM), and graph-based label spreading (LS). Load loss, generation loss, line trip, and bus fault are four important event categories that may be classified using features extracted from synthetic PMU data using modal analysis. By comparing various methods on the South Carolina 500- Bus synthetic network, we find that graph-based LS is the most effective, demonstrating the usefulness of data-driven SSL techniques for detecting events in large-scale power systems. For real-time monitoring and analysis, data-driven methods are becoming crucial due to the growing integration of Phasor Measurement Units (PMUs) and developments in data science. Unfortunately, fully supervised learning methods aren’t very effective because it’s hard to get enough labeled data, which is a problem because some grid events are rare and unclear. Because of its ability to use both labelled and unlabeled data to enhance performance, semi-supervised learning (SSL) becomes a potent option.
Keywords
Semi-supervisedEventIdentificationPowerDetection. I
Citation record
How to cite this article
Anuradha Krishna (2025). Data-Driven Semi-Supervised Approaches for Event Identification in Large-Scale Power Systems. Procedure International Journal of Science and Technology, 2(1), 1–12. https://www.pijst.com/article/pijst21j25001/data-driven-semi-supervised-approaches-for-event-identification-in-large-scale-power-systems
Anuradha Krishna. “Data-Driven Semi-Supervised Approaches for Event Identification in Large-Scale Power Systems.” Procedure International Journal of Science and Technology, vol. 2, no. 1, 2025, pp. 1–12. https://www.pijst.com/article/pijst21j25001/data-driven-semi-supervised-approaches-for-event-identification-in-large-scale-power-systems
Anuradha Krishna. “Data-Driven Semi-Supervised Approaches for Event Identification in Large-Scale Power Systems.” Procedure International Journal of Science and Technology 2, no. 1 (2025): 1–12. https://www.pijst.com/article/pijst21j25001/data-driven-semi-supervised-approaches-for-event-identification-in-large-scale-power-systems
Anuradha Krishna (2025) ‘Data-Driven Semi-Supervised Approaches for Event Identification in Large-Scale Power Systems’, Procedure International Journal of Science and Technology, 2(1), pp. 1–12. Available at: https://www.pijst.com/article/pijst21j25001/data-driven-semi-supervised-approaches-for-event-identification-in-large-scale-power-systems.
Anuradha Krishna, “Data-Driven Semi-Supervised Approaches for Event Identification in Large-Scale Power Systems,” Procedure International Journal of Science and Technology, vol. 2, no. 1, pp. 1–12, 2025. https://www.pijst.com/article/pijst21j25001/data-driven-semi-supervised-approaches-for-event-identification-in-large-scale-power-systems.
Anuradha Krishna. Data-Driven Semi-Supervised Approaches for Event Identification in Large-Scale Power Systems. Procedure International Journal of Science and Technology. 2025;2(1):1–12. https://www.pijst.com/article/pijst21j25001/data-driven-semi-supervised-approaches-for-event-identification-in-large-scale-power-systems.
Anuradha Krishna. Data-Driven Semi-Supervised Approaches for Event Identification in Large-Scale Power Systems. Procedure International Journal of Science and Technology 2025, 2 (1), 1–12. https://www.pijst.com/article/pijst21j25001/data-driven-semi-supervised-approaches-for-event-identification-in-large-scale-power-systems.
No separate funding declaration was available in the verified source record; the journal policy applies.
Conflict of Interest
No separate conflict-of-interest declaration was available in the verified source record; the journal policy applies.
Ethical Approval
No separate ethical approval statement was available in the verified source record; the article and journal policies apply.
Data Availability
No separate data-availability statement was available in the verified source record; contact the author(s) or editorial office where appropriate.
Author Contributions
No separate author-contribution statement was available in the verified source record; authorship follows the published article record.
AI-use Declaration
No separate AI-use declaration was available in the verified source record; the journal AI-use policy applies.
Editorial record
Publisher's Note
The views, opinions and conclusions expressed in this article are those of the author(s). Publication does not imply endorsement by the journal, editorial board or publisher. Responsibility for accuracy, originality and integrity remains with the author(s). Readers should independently evaluate and verify information before application or citation.
Yuan, Yuxuan & Wang, Yanchao & Wang, Zhaoyu. (2023). A Data-Driven Framework for Power System Event Type Identification via Safe Semi-Supervised Techniques. IEEE Transactions on Power Systems. PP. 1-12. 10.1109/ TPWRS.2023.3266153.
Sen, Debarshi & Aghazadeh, Amirali & Mousavi, Ali & Nagarajaiah, Satish & Baraniuk, Richard & Dabak, Anand. (2019). Data-driven semi-supervised and supervised learning algorithms for health monitoring of pipes. Mechanical Systems and Signal Processing. 131. 524-537. 10.1016/j.ymssp.2019.06.003. https://doi.org/10.1016/j.ymssp.2019.06.003
Zhou, Yuxun & Arghandeh, Reza & Konstantakopoulos, Ioannis & Abdullah, Shayaan & Spanos, Costas. (2016). Data-driven event detection with partial knowledge: A Hidden Structure Semi-Supervised learning method. 5962-5968. 10.1109/ACC.2016.7526605. https://doi.org/10.1109/ACC.2016.7526605
Zhou, Yuxun & Arghandeh, Reza & Spanos, Costas. (2017). Partial Knowledge Data-Driven Event Detection for Power Distribution Networks. IEEE Transactions on Smart Grid. PP. 1-1. 10.1109/TSG.2017.2681962. https://doi.org/10.1109/TSG.2017.2681962
Michele Di Santo, Alfredo Vaccaro, Domenico Villacci, and EugenioZimeo. A distributed architecture for online power systems securityanalysis. IEEE Transactions on Industrial Electronics, 51(6):1238–1248,2004.
Ahmed Naufal AL-Masri, Mohd Zainal Abidin Ab Kadir, Hashim Hizam,and Norman Mariun. A novel implementation for generator rotor anglestability prediction using an adaptive articial neural network applicationfor dynamic security assessment. IEEE Transactions on Power Systems,28(3):2516–2525, 2013.
Louis Wehenkel. Machine learning approaches to power-system security assessment. IEEE Expert, 12(5):60–72, 1997.
Pudi Sekhar and Sanjeeb Mohanty. An online power system static securityassessment module using multi-layer perceptron and radial basis functionnetwork. International Journal of Electrical Power & Energy Systems,76:165–173, 2016.
C Fatih Kucuktezcan and VM Istemihan Genc. A new dynamic securityenhancement method via genetic algorithms integrated with neural network based tools. Electric Power Systems Research, 83(1):1–8, 2012.
Emmanouil M Voumvoulakis and Nikos D Hatziargyriou. A particleswarm optimization method for power system dynamic security control.IEEE Transactions on Power Systems, 25(2):1032–1041, 2009.
FengJi Luo, ZhaoYang Dong, Guo Chen, Yan Xu, Ke Meng, YingYingChen, and KitPo Wong. Advanced pattern discovery-based fuzzy clas-sication method for power system dynamic security assessment. IEEETransactions on Industrial Informatics, 11(2):416–426, 2015.
Nikita V Tomin, Victor G Kurbatsky, Denis N Sidorov, and Alexey VZhukov. Machine learning techniques for power system security assess-ment. IFACPapersOnLine, 49(27):445–450, 2016.
Ali Sharifzadeh, Mohammad Taghi Ameli, and Sasan Azad. Powersystem challenges and issues. Application of Machine Learning and DeepLearning Methods to Power System Problems, pages 1–17, 2021.
Ali Mollaiee, Mohammad Taghi Ameli, Sasan Azad, Morteza Nazari-Heris, and (Online) Somayeh Asadi. Data-driven power system security assessmentusing high content database during the covid-19 pandemic. InternationalJournal of Electrical Power & Energy Systems, 150:109077, 2023.
Jochen L Cremer, Ioannis Konstantelos, Simon H Tindemans, and GoranStrbac. Data-driven power system operation: Exploring the balancebetween cost and risk. IEEE Transactions on Power Systems, 34(1):791–801, 2018.
Lipeng Zhu and David J Hill. Data/model jointly driven high-qualitycase generation for power system dynamic stability assessment. IEEETransactions on Industrial Informatics, 18(8):5055–5066, 2021.
Lipeng Zhu, David J Hill, and Chao Lu. Semi-supervised ensemble learn-ing framework for accelerating power system transient stability knowledgebase generation. IEEE Transactions on Power Systems, 37(3):2441–2454,2021.
Kegang Hao and Qun Wan. Importance sampling based direct maximumlikelihood position determination of multiple emitters using nite mea-surements. Signal Processing, 186:108111, 2021.
