Detecting and Interpreting Faults in Vulnerable Power Grids With Machine Learning
Unscheduled power disturbances cause severe consequences both for customers and grid operators. To defend against such events, it is necessary to identify the causes of interruptions in the power distribution network. In this work, we focus on the power grid of a Norwegian community in the Arctic th...
Published in: | IEEE Access |
---|---|
Main Authors: | , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
IEEE
2021
|
Subjects: | |
Online Access: | https://hdl.handle.net/10037/23888 https://doi.org/10.1109/ACCESS.2021.3127042 |
id |
ftunivtroemsoe:oai:munin.uit.no:10037/23888 |
---|---|
record_format |
openpolar |
spelling |
ftunivtroemsoe:oai:munin.uit.no:10037/23888 2023-05-15T15:08:27+02:00 Detecting and Interpreting Faults in Vulnerable Power Grids With Machine Learning Chiesa, Matteo Bianchi, Filippo Maria Eikeland, Odin Foldvik Holmstrand, Inga Setså Bakkejord, Sigurd 2021-11-10 https://hdl.handle.net/10037/23888 https://doi.org/10.1109/ACCESS.2021.3127042 eng eng IEEE IEEE Access O. F. Eikeland, I. S. Holmstrand, S. Bakkejord, M. Chiesa and F. M. Bianchi, "Detecting and Interpreting Faults in Vulnerable Power Grids With Machine Learning," in IEEE Access, vol. 9, 2021 FRIDAID 1977817 doi:10.1109/ACCESS.2021.3127042 2169-3536 https://hdl.handle.net/10037/23888 openAccess Copyright 2021 The Author(s) Journal article Tidsskriftartikkel Peer reviewed publishedVersion 2021 ftunivtroemsoe https://doi.org/10.1109/ACCESS.2021.3127042 2022-02-02T23:57:54Z Unscheduled power disturbances cause severe consequences both for customers and grid operators. To defend against such events, it is necessary to identify the causes of interruptions in the power distribution network. In this work, we focus on the power grid of a Norwegian community in the Arctic that experiences several faults whose sources are unknown. First, we construct a data set consisting of relevant meteorological data and information about the current power quality logged by power-quality meters. Then, we adopt machine-learning techniques to predict the occurrence of faults. Experimental results show that both linear and non-linear classifiers achieve good classification performance. This indicates that the considered power quality and weather variables explain well the power disturbances. Interpreting the decision process of the classifiers provides valuable insights to understand the main causes of disturbances. Traditional features selection methods can only indicate which are the variables that, on average, mostly explain the fault occurrences in the dataset. Besides providing such a global interpretation, it is also important to identify the specific set of variables that explain each individual fault. To address this challenge, we adopt a recent technique to interpret the decision process of a deep learning model, called Integrated Gradients. The proposed approach allows gaining detailed insights on the occurrence of a specific fault, which are valuable for the distribution system operators to implement strategies to prevent and mitigate power disturbances. Article in Journal/Newspaper Arctic University of Tromsø: Munin Open Research Archive Arctic IEEE Access 9 150686 150699 |
institution |
Open Polar |
collection |
University of Tromsø: Munin Open Research Archive |
op_collection_id |
ftunivtroemsoe |
language |
English |
description |
Unscheduled power disturbances cause severe consequences both for customers and grid operators. To defend against such events, it is necessary to identify the causes of interruptions in the power distribution network. In this work, we focus on the power grid of a Norwegian community in the Arctic that experiences several faults whose sources are unknown. First, we construct a data set consisting of relevant meteorological data and information about the current power quality logged by power-quality meters. Then, we adopt machine-learning techniques to predict the occurrence of faults. Experimental results show that both linear and non-linear classifiers achieve good classification performance. This indicates that the considered power quality and weather variables explain well the power disturbances. Interpreting the decision process of the classifiers provides valuable insights to understand the main causes of disturbances. Traditional features selection methods can only indicate which are the variables that, on average, mostly explain the fault occurrences in the dataset. Besides providing such a global interpretation, it is also important to identify the specific set of variables that explain each individual fault. To address this challenge, we adopt a recent technique to interpret the decision process of a deep learning model, called Integrated Gradients. The proposed approach allows gaining detailed insights on the occurrence of a specific fault, which are valuable for the distribution system operators to implement strategies to prevent and mitigate power disturbances. |
format |
Article in Journal/Newspaper |
author |
Chiesa, Matteo Bianchi, Filippo Maria Eikeland, Odin Foldvik Holmstrand, Inga Setså Bakkejord, Sigurd |
spellingShingle |
Chiesa, Matteo Bianchi, Filippo Maria Eikeland, Odin Foldvik Holmstrand, Inga Setså Bakkejord, Sigurd Detecting and Interpreting Faults in Vulnerable Power Grids With Machine Learning |
author_facet |
Chiesa, Matteo Bianchi, Filippo Maria Eikeland, Odin Foldvik Holmstrand, Inga Setså Bakkejord, Sigurd |
author_sort |
Chiesa, Matteo |
title |
Detecting and Interpreting Faults in Vulnerable Power Grids With Machine Learning |
title_short |
Detecting and Interpreting Faults in Vulnerable Power Grids With Machine Learning |
title_full |
Detecting and Interpreting Faults in Vulnerable Power Grids With Machine Learning |
title_fullStr |
Detecting and Interpreting Faults in Vulnerable Power Grids With Machine Learning |
title_full_unstemmed |
Detecting and Interpreting Faults in Vulnerable Power Grids With Machine Learning |
title_sort |
detecting and interpreting faults in vulnerable power grids with machine learning |
publisher |
IEEE |
publishDate |
2021 |
url |
https://hdl.handle.net/10037/23888 https://doi.org/10.1109/ACCESS.2021.3127042 |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic |
genre_facet |
Arctic |
op_relation |
IEEE Access O. F. Eikeland, I. S. Holmstrand, S. Bakkejord, M. Chiesa and F. M. Bianchi, "Detecting and Interpreting Faults in Vulnerable Power Grids With Machine Learning," in IEEE Access, vol. 9, 2021 FRIDAID 1977817 doi:10.1109/ACCESS.2021.3127042 2169-3536 https://hdl.handle.net/10037/23888 |
op_rights |
openAccess Copyright 2021 The Author(s) |
op_doi |
https://doi.org/10.1109/ACCESS.2021.3127042 |
container_title |
IEEE Access |
container_volume |
9 |
container_start_page |
150686 |
op_container_end_page |
150699 |
_version_ |
1766339817584459776 |