Fault Detection Utilizing Convolution Neural Network on Timeseries Synchrophasor Data From Phasor Measurement Units

Alqudah, Mohammad Khaled; Pavlovski, Martin; Dokic, Tatjana; Kezunovic, Mladen; Hu, Yi; Obradovic, Zoran

doi:10.1109/tpwrs.2021.3135336

Fault Detection Utilizing Convolution Neural Network on Timeseries Synchrophasor Data From Phasor Measurement Units

Journal Article · Mon Dec 13 23:00:00 EST 2021 · IEEE Transactions on Power Systems

DOI:https://doi.org/10.1109/tpwrs.2021.3135336· OSTI ID:1874491

Alqudah, Mohammad Khaled ^[1]; Pavlovski, Martin ^[2]; Dokic, Tatjana ^[3]; Kezunovic, Mladen ^[3]; Hu, Yi ^[4]; Obradovic, Zoran ^[2]

Temple Univ., Philadelphia, PA (United States); Texas A&M University
Temple Univ., Philadelphia, PA (United States)
Texas A & M Univ., College Station, TX (United States)
Quanta Technology, Raleigh, NC (United States)

An end-to-end supervised learning method is proposed for fault detection in the electric grid using Big Data from multiple Phasor Measurement Units (PMUs). The approach consists of preprocessing steps aimed at reducing data noise and dimensionality, followed by utilization of six classification models considered for detecting faults. Three of the models were variants of Convolutional Neural Network (CNN) architectures that consider a single type of measurement (voltage, current or frequency) at all PMUs or all types together also at all PMUs. CNN based models were compared to traditional methods of Logistic Regression (LR), Multi-layer Perceptron (MLP) and Support Vector Machine (SVM). Evaluation was conducted on two-year data measured by PMUs at 37 locations in a large electric grid. Here, the response variable for classification were extracted from the grid-wide outage event log. Experiments show that CNN-based models outperformed traditional methods on one year out-of-sample outage detection over the entire grid.

Research Organization:: Texas A & M Univ., College Station, TX (United States). Texas A&M Engineering Experiment Station

Sponsoring Organization:: USDOE

Grant/Contract Number:: OE0000913

OSTI ID:: 1874491

Journal Information:: IEEE Transactions on Power Systems, Journal Name: IEEE Transactions on Power Systems Journal Issue: 5 Vol. 37; ISSN 0885-8950

Publisher:: IEEECopyright Statement

Country of Publication:: United States

Language:: English

References (13)

Time series shapelets: a novel technique that allows accurate, interpretable and fast classification Ye, Lexiang; Keogh, Eamonn Data Mining and Knowledge Discovery, Vol. 22, Issue 1-2 https://doi.org/10.1007/s10618-010-0179-5	journal	June 2010
The great time series classification bake off: a review and experimental evaluation of recent algorithmic advances Bagnall, Anthony; Lines, Jason; Bostrom, Aaron Data Mining and Knowledge Discovery, Vol. 31, Issue 3 https://doi.org/10.1007/s10618-016-0483-9	journal	November 2016
Big data analytics for future electricity grids Kezunovic, Mladen; Pinson, Pierre; Obradovic, Zoran Electric Power Systems Research, Vol. 189 https://doi.org/10.1016/j.epsr.2020.106788	journal	December 2020
Wide Area Measurement Based Online Monitoring and Event Detection Using Convolutional Neural Networks Kesici, Mert; Saner, Can Berk; Mahdi, Mohammed 2019 7th International Istanbul Smart Grids and Cities Congress and Fair (ICSG) https://doi.org/10.1109/SGCF.2019.8782365	conference	April 2019
Power Grid Online Surveillance Through PMU-Embedded Convolutional Neural Networks Wang, Shiyuan; Dehghanian, Payman; Li, Li IEEE Transactions on Industry Applications, Vol. 56, Issue 2 https://doi.org/10.1109/TIA.2019.2958786	journal	March 2020
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
Dimensionality Reduction of Synchrophasor Data for Early Event Detection: Linearized Analysis Xie, Le; Chen, Yang; Kumar, P. R. IEEE Transactions on Power Systems, Vol. 29, Issue 6 https://doi.org/10.1109/TPWRS.2014.2316476	journal	November 2014
Identifying Overlapping Successive Events Using a Shallow Convolutional Neural Network Li, Wenting; Wang, Meng IEEE Transactions on Power Systems, Vol. 34, Issue 6 https://doi.org/10.1109/TPWRS.2019.2914774	journal	November 2019
Real-Time Faulted Line Localization and PMU Placement in Power Systems Through Convolutional Neural Networks Li, Wenting; Deka, Deepjyoti; Chertkov, Michael IEEE Transactions on Power Systems, Vol. 34, Issue 6 https://doi.org/10.1109/TPWRS.2019.2917794	journal	November 2019
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
Real-Time Multiple Event Detection and Classification Using Moving Window PCA Rafferty, Mark; Liu, Xueqin; Laverty, David M. IEEE Transactions on Smart Grid, Vol. 7, Issue 5 https://doi.org/10.1109/TSG.2016.2559444	journal	September 2016
Frequency Disturbance Event Detection Based on Synchrophasors and Deep Learning Wang, Weikang; Yin, He; Chen, Chang IEEE Transactions on Smart Grid, Vol. 11, Issue 4 https://doi.org/10.1109/TSG.2020.2971909	journal	July 2020

Similar Records

Line Faults Classification Using Machine Learning on Three Phase Voltages Extracted from Large Dataset of PMU Measurements

Conference · Mon Jan 03 23:00:00 EST 2022 · Proceedings of the Annual Hawaii International Conference on System Sciences Proceedings of the 55th Hawaii International Conference on System Sciences · OSTI ID:1874493

Line Faults Classification Using Machine Learning on Three Phase Voltages Extracted from Large Dataset of PMU Measurements

Journal Article · Mon Jan 03 23:00:00 EST 2022 · Proceedings of the Annual Hawaii International Conference on System Sciences · OSTI ID:1891312

Identification of topology changes in power grids using phasor measurements

Journal Article · Sun Nov 16 23:00:00 EST 2014 · Applied Stochastic Models in Business and Industry · OSTI ID:1401593

Related Subjects

42 ENGINEERING
Big data applications
Convolutional neural networks
Dimensionality reduction
Event detection
Machine learning
Neural networks
Phasor measurement units
Power system faults
Smart grids
Time series analysis

Fault Detection Utilizing Convolution Neural Network on Timeseries Synchrophasor Data From Phasor Measurement Units

Citation Formats

References (13)

Similar Records

Related Subjects