Siamese Sigmoid Networks for the open classification of grid disturbances in power transmission systems
Abstract The online classification of grid disturbances is an important prerequisite for an automated and reliable operation of power transmission systems. Most of the state‐of‐the‐art approaches assume that all classes are already known in the training phase and cannot handle new disturbance events...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2023-04-01
|
Series: | IET Smart Grid |
Online Access: | https://doi.org/10.1049/stg2.12083 |
_version_ | 1797845681564549120 |
---|---|
author | André Kummerow Mohammad Dirbas Cristian Monsalve Peter Bretschneider |
author_facet | André Kummerow Mohammad Dirbas Cristian Monsalve Peter Bretschneider |
author_sort | André Kummerow |
collection | DOAJ |
description | Abstract The online classification of grid disturbances is an important prerequisite for an automated and reliable operation of power transmission systems. Most of the state‐of‐the‐art approaches assume that all classes are already known in the training phase and cannot handle new disturbance events, which appear in the application phase and lead to severe misclassifications. To mitigate this shortcoming, the disturbance detection is investigated as an open classification task and a novel recurrent Siamese neural network architecture is introduced to identify and locate known and unknown disturbance events from phasor measurements. Extending preliminary work, a probabilistic distance‐based classification approach with an integrated rejection mechanism is presented, which enables to learn class‐dependent decision boundaries and margins to reduce the open‐set risk. A detailed performance analysis is presented including multiple benchmark methods in different closed‐set and open‐set classification tasks for a simulated power transmission system. Additionally, a limited and full observability of the grid with phasor measurements are addressed in the experiments. |
first_indexed | 2024-04-09T17:42:56Z |
format | Article |
id | doaj.art-90bcef2b47af4744bc2f794d3ddb5586 |
institution | Directory Open Access Journal |
issn | 2515-2947 |
language | English |
last_indexed | 2024-04-09T17:42:56Z |
publishDate | 2023-04-01 |
publisher | Wiley |
record_format | Article |
series | IET Smart Grid |
spelling | doaj.art-90bcef2b47af4744bc2f794d3ddb55862023-04-16T13:55:16ZengWileyIET Smart Grid2515-29472023-04-016213614610.1049/stg2.12083Siamese Sigmoid Networks for the open classification of grid disturbances in power transmission systemsAndré Kummerow0Mohammad Dirbas1Cristian Monsalve2Peter Bretschneider3Cognitive Energy Systems, Fraunhofer IOSB IOSB‐AST Ilmenau Fraunhofer Institute of Optronics, System Technologies and Image Exploitation Fraunhofer Center for Machine Learning Ilmenau GermanyCognitive Energy Systems, Fraunhofer IOSB IOSB‐AST Ilmenau Fraunhofer Institute of Optronics, System Technologies and Image Exploitation Fraunhofer Center for Machine Learning Ilmenau GermanyCognitive Energy Systems, Fraunhofer IOSB IOSB‐AST Ilmenau Fraunhofer Institute of Optronics, System Technologies and Image Exploitation Fraunhofer Center for Machine Learning Ilmenau GermanyCognitive Energy Systems, Fraunhofer IOSB IOSB‐AST Ilmenau Fraunhofer Institute of Optronics, System Technologies and Image Exploitation Fraunhofer Center for Machine Learning Ilmenau GermanyAbstract The online classification of grid disturbances is an important prerequisite for an automated and reliable operation of power transmission systems. Most of the state‐of‐the‐art approaches assume that all classes are already known in the training phase and cannot handle new disturbance events, which appear in the application phase and lead to severe misclassifications. To mitigate this shortcoming, the disturbance detection is investigated as an open classification task and a novel recurrent Siamese neural network architecture is introduced to identify and locate known and unknown disturbance events from phasor measurements. Extending preliminary work, a probabilistic distance‐based classification approach with an integrated rejection mechanism is presented, which enables to learn class‐dependent decision boundaries and margins to reduce the open‐set risk. A detailed performance analysis is presented including multiple benchmark methods in different closed‐set and open‐set classification tasks for a simulated power transmission system. Additionally, a limited and full observability of the grid with phasor measurements are addressed in the experiments.https://doi.org/10.1049/stg2.12083 |
spellingShingle | André Kummerow Mohammad Dirbas Cristian Monsalve Peter Bretschneider Siamese Sigmoid Networks for the open classification of grid disturbances in power transmission systems IET Smart Grid |
title | Siamese Sigmoid Networks for the open classification of grid disturbances in power transmission systems |
title_full | Siamese Sigmoid Networks for the open classification of grid disturbances in power transmission systems |
title_fullStr | Siamese Sigmoid Networks for the open classification of grid disturbances in power transmission systems |
title_full_unstemmed | Siamese Sigmoid Networks for the open classification of grid disturbances in power transmission systems |
title_short | Siamese Sigmoid Networks for the open classification of grid disturbances in power transmission systems |
title_sort | siamese sigmoid networks for the open classification of grid disturbances in power transmission systems |
url | https://doi.org/10.1049/stg2.12083 |
work_keys_str_mv | AT andrekummerow siamesesigmoidnetworksfortheopenclassificationofgriddisturbancesinpowertransmissionsystems AT mohammaddirbas siamesesigmoidnetworksfortheopenclassificationofgriddisturbancesinpowertransmissionsystems AT cristianmonsalve siamesesigmoidnetworksfortheopenclassificationofgriddisturbancesinpowertransmissionsystems AT peterbretschneider siamesesigmoidnetworksfortheopenclassificationofgriddisturbancesinpowertransmissionsystems |