Uncertainty Quantification of Capacitor Switching Transient Location using Machine Learning

Wilson, Aaron J.; Tran, Hoang; Lu, Dan

doi:10.1109/tpwrs.2023.3286173

Uncertainty Quantification of Capacitor Switching Transient Location using Machine Learning

Journal Article · Wed Jun 14 00:00:00 EDT 2023 · IEEE Transactions on Power Systems

DOI:https://doi.org/10.1109/tpwrs.2023.3286173· OSTI ID:2000425

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

Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)

Identification of capacitor switching transient location provides valuable insight into the state of the associated equipment. Machine learning (ML) models, and convolutional neural networks (CNNs) in particular, have demonstrated remarkable performance in signal location. However, ML models are data driven whose predictions are affected by noise in data and may also suffer from large extrapolation errors when applied to new conditions. Uncertainty quantification (UQ) is necessary to ensure model trustworthiness and avoid overconfident predictions in extrapolation. Here, in this work, we propose a novel UQ method, called PI3NN, to quantify prediction uncertainty of ML models and integrate the method with CNNs for transient source location. PI3NN calculates Prediction Intervals by training 3 Neural Networks and uses root-finding methods to determine the interval precisely. Additionally, PI3NN can identify out-of-distribution (OOD) data in a nonstationary condition to avoid overconfident prediction. Results indicate that with PI3NN, transient signals are not only correctly identified, but when said signals are subject to corruptions characteristic of an actual power monitoring system (e.g. non-ideal sensors), the model recognizes when it is uncertain about its predictions, effectively letting the user know when to accept or discard the results.

View Accepted Manuscript (DOE)

Research Organization:: Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)

Sponsoring Organization:: USDOE Office of Electricity (OE)

Grant/Contract Number:: AC05-00OR22725

OSTI ID:: 2000425

Journal Information:: IEEE Transactions on Power Systems, Journal Name: IEEE Transactions on Power Systems Journal Issue: 2 Vol. 39; ISSN 0885-8950

Publisher:: IEEECopyright Statement

Country of Publication:: United States

Language:: English

References (18)

Prediction Intervals for Artificial Neural Networks Hwang, J. T. Gene; Ding, A. Adam Journal of the American Statistical Association, Vol. 92, Issue 438 https://doi.org/10.1080/01621459.1997.10474027	journal	June 1997
A direction finder for power quality disturbances based upon disturbance power and energy Parsons, A. C.; Grady, W. M.; Powers, E. J. IEEE Transactions on Power Delivery, Vol. 15, Issue 3 https://doi.org/10.1109/61.871378	journal	July 2000
S-Transform technique for identifying the location of a switched capacitor Bhende, C. N. 2011 10th International Conference on Environment and Electrical Engineering https://doi.org/10.1109/EEEIC.2011.5874846	conference	May 2011
A New Index for Online Tracking of the Switched capacitor bank location in distribution systems Khani, H.; Moallem, M.; Dolatshahi, M. 2010 18th Iranian Conference on Electrical Engineering https://doi.org/10.1109/IRANIANCEE.2010.5506956	conference	May 2010
Determination of Instantaneous Currents and Voltages by Means of Alpha, Beta, and Zero Components Duesterhoeft, W. C.; Schulz, Max W.; Clarke, Edith Transactions of the American Institute of Electrical Engineers, Vol. 70, Issue 2 https://doi.org/10.1109/T-AIEE.1951.5060554	journal	July 1951
On tracking and finding the location of switched capacitor banks in distribution systems Khani, H.; Moallem, M.; Sadri, S. 2009 Transmission & Distribution Conference & Exposition: Asia and Pacific https://doi.org/10.1109/TD-ASIA.2009.5356974	conference	January 2009
A novel algorithm for determining the exact location of switched capacitor banks in distribution systems Khani, H.; Moallem, M.; Sadri, S. 2009 Transmission & Distribution Conference & Exposition: Asia and Pacific https://doi.org/10.1109/TD-ASIA.2009.5356977	conference	October 2009
Effective Transient-Free Capacitor Switching (TFCS) for Large Motor Starting on MV Systems Padimiti, Dwaraka S.; Christian, Michael B.; Jarvinen, Jukka IEEE Transactions on Industry Applications, Vol. 55, Issue 1 https://doi.org/10.1109/TIA.2018.2866810	journal	January 2019
Lower Upper Bound Estimation Method for Construction of Neural Network-Based Prediction Intervals Khosravi, A.; Nahavandi, S.; Creighton, D. IEEE Transactions on Neural Networks, Vol. 22, Issue 3 https://doi.org/10.1109/TNN.2010.2096824	journal	March 2011
An Efficient Approach for Tracking Transients Generated by Utility Shunt Capacitor Switching Chang, G. W.; Shih, M. H.; Chu, S. Y. IEEE Transactions on Power Delivery, Vol. 21, Issue 1 https://doi.org/10.1109/TPWRD.2005.860284	journal	January 2006
Signal Processing-Based Direction Finder for Transient Capacitor Switching Disturbances Shin, Yong-June; Powers, Edward J.; Grady, W. Mack IEEE Transactions on Power Delivery, Vol. 23, Issue 4 https://doi.org/10.1109/TPWRD.2008.2002984	journal	October 2008
On Tracking the Source Location of Voltage Sags and Utility Shunt Capacitor Switching Transients Chang, G. W.; Huang, H. M. IEEE Transactions on Power Delivery, Vol. 23, Issue 4 https://doi.org/10.1109/TPWRD.2008.923143	journal	October 2008
Transient Characteristics Analysis of Shunt Capacitor Asynchronous Energizing Liang, Jiabi; Zhu, Ke IEEE Transactions on Power Delivery, Vol. 35, Issue 5 https://doi.org/10.1109/TPWRD.2019.2963338	journal	October 2020
Predicting good probabilities with supervised learning Niculescu-Mizil, Alexandru; Caruana, Rich Proceedings of the 22nd international conference on Machine learning - ICML '05 https://doi.org/10.1145/1102351.1102430	conference	January 2005
A Practical Bayesian Framework for Backpropagation Networks MacKay, David J. C. Neural Computation, Vol. 4, Issue 3 https://doi.org/10.1162/neco.1992.4.3.448	journal	May 1992
Quantile Regression Koenker, Roger; Hallock, Kevin F. Journal of Economic Perspectives, Vol. 15, Issue 4 https://doi.org/10.1257/jep.15.4.143	journal	November 2001
Prediction Intervals for Neural Networks via Nonlinear Regression de Veaux, Richard D.; Schumi, Jennifer; Schweinsberg, Jason Technometrics, Vol. 40, Issue 4 https://doi.org/10.2307/1270528	journal	November 1998
Regression Quantiles Koenker, Roger; Bassett, Gilbert Econometrica, Vol. 46, Issue 1 https://doi.org/10.2307/1913643	journal	January 1978

Similar Records

Uncertainty quantification of machine learning models to improve streamflow prediction under changing climate and environmental conditions

Journal Article · Thu Apr 20 20:00:00 EDT 2023 · Frontiers in Water · OSTI ID:1972559

Uncertainty quantification of the convolutional neural networks on permeability estimation from micro-CT scanned sandstone and carbonate rock images

Journal Article · Wed Jul 19 20:00:00 EDT 2023 · Geoenergy Science and Engineering · OSTI ID:1997802

Clarifying trust of materials property predictions using neural networks with distribution-specific uncertainty quantification

Journal Article · Tue May 02 20:00:00 EDT 2023 · Machine Learning: Science and Technology · OSTI ID:2422892

Related Subjects

24 POWER TRANSMISSION AND DISTRIBUTION
machine learning
situational awareness
smart grid
transients
uncertainty quantification

Uncertainty Quantification of Capacitor Switching Transient Location using Machine Learning

Citation Formats

References (18)

Similar Records

Related Subjects