A Data-Driven Framework for Power System Event Type Identification via Safe Semi-Supervised Techniques

Yuan, Yuxuan; Wang, Yanchao; Wang, Zhaoyu

doi:10.1109/tpwrs.2023.3266153

A Data-Driven Framework for Power System Event Type Identification via Safe Semi-Supervised Techniques

Journal Article · Wed Apr 10 00:00:00 EDT 2024 · IEEE Transactions on Power Systems

DOI:https://doi.org/10.1109/tpwrs.2023.3266153· OSTI ID:2325009

^[1]; ^[2]; ^[2]

Iowa State Univ., Ames, IA (United States); Iowa State University of Science and Technology
Iowa State Univ., Ames, IA (United States)

Herein this paper investigates the use of phasor measurement unit (PMU) data with deep learning techniques to construct real-time event identification models for transmission networks. Increasing penetration of distributed energy resources represents a great opportunity to achieve decarbonization, as well as challenges in systematic situational awareness. When high-resolution PMU data and sufficient manually recorded event labels are available, the power event identification problem is defined as a statistical classification problem that can be solved by numerous cutting-edge classifiers. However, in real grids, collecting tremendous high-quality event labels is quite expensive. Utilities frequently have a large number of event records without in-depth details (i.e., unlabeled events). To bridge this gap, we propose a novel semi-supervised learning-based method to improve the performance of event classifiers trained with a limited number of labeled events by exploiting the information from massive unlabeled events. In other words, compared to existing data-driven methods, our method requires only a small portion of labeled data to achieve a similar level of accuracy. Meanwhile, this work discusses and addresses the performance degradation caused by class distribution mismatch between the training set and the real applications. Based on the proposed safe learning mechanism, our model does not directly use all unlabeled events during model training, but selectively uses them through a comprehensive evaluation procedure. Numerical studies on a sizable PMU dataset have been used to validate the performance of the proposed method.

View Accepted Manuscript (DOE)

Research Organization:: Iowa State Univ., Ames, IA (United States)

Sponsoring Organization:: National Science Foundation (NSF); USDOE Office of Electricity (OE)

Grant/Contract Number:: OE0000910

OSTI ID:: 2325009

Journal Information:: IEEE Transactions on Power Systems, Journal Name: IEEE Transactions on Power Systems Journal Issue: 1 Vol. 39; ISSN 0885-8950

Publisher:: IEEECopyright Statement

Country of Publication:: United States

Language:: English

References (31)

Revisiting Consistency Regularization for Semi-supervised Learning Fan, Yue; Kukleva, Anna; Schiele, Bernt Lecture Notes in Computer Science https://doi.org/10.1007/978-3-030-92659-5_5	book	January 2021
Learning from noisy examples Angluin, Dana; Laird, Philip Machine Learning, Vol. 2, Issue 4 https://doi.org/10.1007/BF00116829	journal	April 1988
A pattern recognition methodology for evaluation of load profiles and typical days of large electricity customers Tsekouras, G. J.; Kotoulas, P. B.; Tsirekis, C. D. Electric Power Systems Research, Vol. 78, Issue 9 https://doi.org/10.1016/j.epsr.2008.01.010	journal	September 2008
WAMS-based two-level robust detection methodology of power system events Lopes, Gabriel V. de S.; Moraes, Guido R.; Issicaba, Diego Sustainable Energy, Grids and Networks, Vol. 31 https://doi.org/10.1016/j.segan.2022.100689	journal	September 2022
Randomizing Outputs to Increase Prediction Accuracy Breiman, Leo Machine Learning, Vol. 40, Issue 3, p. 229-242 https://doi.org/10.1023/A:1007682208299	journal	September 2000
Transfer Learning for Event Detection From PMU Measurements With Scarce Labels Hai, Ameen Abdel; Dokic, Tatjana; Pavlovski, Martin IEEE Access, Vol. 9 https://doi.org/10.1109/ACCESS.2021.3111727	journal	January 2021
Unsupervised Power System Event Detection and Classification Using Unlabeled PMU Data Lan, Tu; Lin, You; Wang, Jianhui 2021 IEEE PES Innovative Smart Grid Technologies Europe (ISGT Europe) https://doi.org/10.1109/ISGTEurope52324.2021.9639995	conference	October 2021
A PMU-Based Data-Driven Approach for Classifying Power System Events Considering Cyberattacks Ma, Rui; Basumallik, Sagnik; Eftekharnejad, Sara IEEE Systems Journal, Vol. 14, Issue 3 https://doi.org/10.1109/JSYST.2019.2963546	journal	September 2020
Preliminary work to classify the disturbance events recorded by phasor measurement units Dahal, O. P.; Brahma, S. M. 2012 IEEE Power and Energy Society General Meeting https://doi.org/10.1109/PESGM.2012.6344715	conference	July 2012
An Unsupervised Learning Framework for Event Detection, Type Identification and Localization Using PMUs Without Any Historical Labels Li, Haoran; Weng, Yang; Farantatos, Evangelos 2019 IEEE Power & Energy Society General Meeting (PESGM) https://doi.org/10.1109/PESGM40551.2019.8973580	conference	August 2019
Real-time Event Detection Using Rank Signatures of Real-world PMU Data Ghasemkhani, Amir; Liu, Yunchuan; Yang, Lei 2022 IEEE Power & Energy Society General Meeting (PESGM) https://doi.org/10.1109/PESGM48719.2022.9917156	conference	July 2022
Event Detection and Its Signal Characterization in PMU Data Stream Negi, Sanjay Singh; Kishor, Nand; Uhlen, Kjetil IEEE Transactions on Industrial Informatics, Vol. 13, Issue 6 https://doi.org/10.1109/TII.2017.2731366	journal	December 2017
A New Approach to Power System Disturbance Assessment Using Wide-Area Postdisturbance Records Jena, Manas Kumar; Panigrahi, Bijaya Ketan; Samantaray, Subhransu Ranjan IEEE Transactions on Industrial Informatics, Vol. 14, Issue 3 https://doi.org/10.1109/TII.2017.2772081	journal	March 2018
Tri-training: exploiting unlabeled data using three classifiers No authors listed IEEE Transactions on Knowledge and Data Engineering, Vol. 17, Issue 11 https://doi.org/10.1109/TKDE.2005.186	journal	November 2005
Comprehensive Clustering of Disturbance Events Recorded by Phasor Measurement Units Dahal, Om P.; Brahma, Sukumar M.; Cao, Huiping IEEE Transactions on Power Delivery, Vol. 29, Issue 3 https://doi.org/10.1109/TPWRD.2013.2285097	journal	June 2014
Supervisory Protection and Automated Event Diagnosis Using PMU Data Biswal, Milan; Brahma, Sukumar M.; Cao, Huiping IEEE Transactions on Power Delivery, Vol. 31, Issue 4 https://doi.org/10.1109/TPWRD.2016.2520958	journal	August 2016
Real-Time Identification of Dynamic Events in Power Systems Using PMU Data, and Potential Applications—Models, Promises, and Challenges Brahma, S.; Kavasseri, R.; Cao, H. IEEE Transactions on Power Delivery, Vol. 32, Issue 1 https://doi.org/10.1109/TPWRD.2016.2590961	journal	February 2017
The Characteristic Ellipsoid Methodology and its Application in Power Systems Ma, Jian; Makarov, Yuri V.; Diao, Ruisheng IEEE Transactions on Power Systems, Vol. 27, Issue 4 https://doi.org/10.1109/TPWRS.2012.2195232	journal	November 2012
Real-Time Event Identification Through Low-Dimensional Subspace Characterization of High-Dimensional Synchrophasor Data Li, Wenting; Wang, Meng; Chow, Joe H. IEEE Transactions on Power Systems, Vol. 33, Issue 5 https://doi.org/10.1109/TPWRS.2018.2796442	journal	September 2018
Power System Event Identification Based on Deep Neural Network With Information Loading Shi, Jie; Foggo, Brandon; Yu, Nanpeng IEEE Transactions on Power Systems, Vol. 36, Issue 6 https://doi.org/10.1109/TPWRS.2021.3080279	journal	November 2021
Learning-Based Real-Time Event Identification Using Rich Real PMU Data Yuan, Yuxuan; Guo, Yifei; Dehghanpour, Kaveh IEEE Transactions on Power Systems, Vol. 36, Issue 6 https://doi.org/10.1109/TPWRS.2021.3081608	journal	November 2021
A Transfer Learning Framework for Power System Event Identification Li, Haoran; Ma, Zhihao; Weng, Yang IEEE Transactions on Power Systems, Vol. 37, Issue 6 https://doi.org/10.1109/TPWRS.2022.3153445	journal	November 2022
Learning Latent Interactions for Event Classification via Graph Neural Networks and PMU Data Yuan, Yuxuan; Wang, Zhaoyu; Wang, Yanchao IEEE Transactions on Power Systems, Vol. 38, Issue 1 https://doi.org/10.1109/TPWRS.2022.3158248	journal	January 2023
Synchronized Phasor Measurement Applications in Power Systems De La Ree, Jaime; Centeno, Virgilio; Thorp, James S. IEEE Transactions on Smart Grid, Vol. 1, Issue 1 https://doi.org/10.1109/TSG.2010.2044815	journal	June 2010
Power System Real-Time Event Detection and Associated Data Archival Reduction Based on Synchrophasors Ge, Yinyin; Flueck, Alexander J.; Kim, Dae-Kyeong IEEE Transactions on Smart Grid, Vol. 6, Issue 4 https://doi.org/10.1109/TSG.2014.2383693	journal	July 2015
Wavelet-Based Event Detection Method Using PMU Data Kim, Do-In; Chun, Tae Yoon; Yoon, Sung-Hwa IEEE Transactions on Smart Grid, Vol. 8, Issue 3 https://doi.org/10.1109/TSG.2015.2478421	journal	May 2017
Data-Driven Event Detection of Power Systems Based on Unequal-Interval Reduction of PMU Data and Local Outlier Factor Liu, Shengyuan; Zhao, Yuxuan; Lin, Zhenzhi IEEE Transactions on Smart Grid, Vol. 11, Issue 2 https://doi.org/10.1109/TSG.2019.2941565	journal	March 2020
Robust Event Classification Using Imperfect Real-World PMU Data Liu, Yunchuan; Yang, Lei; Ghasemkhani, Amir IEEE Internet of Things Journal, Vol. 10, Issue 9 https://doi.org/10.1109/jiot.2022.3177686	journal	May 2023
Structural Tensor Learning for Event Identification With Limited Labels Li, Haoran; Ma, Zhihao; Weng, Yang IEEE Transactions on Power Systems, Vol. 38, Issue 6 https://doi.org/10.1109/tpwrs.2022.3231262	journal	November 2023
The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation Chicco, Davide; Jurman, Giuseppe BMC Genomics, Vol. 21, Issue 1 https://doi.org/10.1186/s12864-019-6413-7	journal	January 2020
Bad Data Detection Algorithm for PMU Based on Spectral Clustering Yang, Zhiwei; Liu, Hao; Bi, Tianshu Journal of Modern Power Systems and Clean Energy, Vol. 8, Issue 3 https://doi.org/10.35833/MPCE.2019.000457	journal	January 2020

Similar Records

Weakly Supervised Event Classification Using Imperfect Real-world PMU Data with Scarce Labels

Conference · Sun Jul 17 00:00:00 EDT 2022 · 2022 IEEE Power & Energy Society General Meeting (PESGM) · OSTI ID:1958826

Learning Latent Interactions for Event Identification via Graph Neural Networks and PMU Data

Journal Article · Wed Mar 09 19:00:00 EST 2022 · IEEE Transactions on Power Systems · OSTI ID:1866732

Robust Event Classification Using Imperfect Real-world PMU Data

Journal Article · Mon May 23 20:00:00 EDT 2022 · IEEE Internet of Things Journal (Online) · OSTI ID:1958801

Related Subjects

42 ENGINEERING
event identification
phasor measurement unit
safe learning
semi-supervised model
unlabeled event

A Data-Driven Framework for Power System Event Type Identification via Safe Semi-Supervised Techniques

Citation Formats

References (31)

Similar Records

Related Subjects