End-to-end deep learning on classification of neutral-to-ground voltage in secondary distribution systems

Neutral-to-ground voltage (NTGV) abnormalities in secondary distribution systems (SDS) pose significant power quality (PQ) challenges, including safety hazards, power losses, and equipment damage. Despite their importance, these abnormalities remain relatively understudied. Accurate classification o...

Full description

Bibliographic Details
Published in:e-Prime - Advances in Electrical Engineering, Electronics and Energy
Main Author: Mahadan M.E.; Abidin A.F.; Yusoh M.A.T.M.; Hairuddin M.A.; Ashar N.D.K.
Format: Article
Language:English
Published: Elsevier Ltd 2024
Online Access:https://www.scopus.com/inward/record.uri?eid=2-s2.0-85205468209&doi=10.1016%2fj.prime.2024.100795&partnerID=40&md5=f2133056531d516465b8b8403a9b5ea3
id 2-s2.0-85205468209
spelling 2-s2.0-85205468209
Mahadan M.E.; Abidin A.F.; Yusoh M.A.T.M.; Hairuddin M.A.; Ashar N.D.K.
End-to-end deep learning on classification of neutral-to-ground voltage in secondary distribution systems
2024
e-Prime - Advances in Electrical Engineering, Electronics and Energy
10

10.1016/j.prime.2024.100795
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85205468209&doi=10.1016%2fj.prime.2024.100795&partnerID=40&md5=f2133056531d516465b8b8403a9b5ea3
Neutral-to-ground voltage (NTGV) abnormalities in secondary distribution systems (SDS) pose significant power quality (PQ) challenges, including safety hazards, power losses, and equipment damage. Despite their importance, these abnormalities remain relatively understudied. Accurate classification of NTGV events is crucial for effective mitigation strategies. Existing research primarily relies on machine learning (ML) models trained on manually extracted features from simulated or real-world signals. This paper introduces a novel end-to-end deep learning approach that leverages Gate Recurrent Units (GRU) to bypass manual feature extraction, directly utilizing real-world signals from three NTGV event categories: ground fault, lightning strike, and normal conditions. This is first time that GRU has been used for NTGV classification using raw data. The model's generalizability is assessed through 5-fold cross-validation. A comparative analysis with baseline models and traditional ML techniques demonstrates the proposed model's superior performance and computational efficiency due to its ability to directly process raw data. © 2024
Elsevier Ltd
27726711
English
Article
All Open Access; Gold Open Access
author Mahadan M.E.; Abidin A.F.; Yusoh M.A.T.M.; Hairuddin M.A.; Ashar N.D.K.
spellingShingle Mahadan M.E.; Abidin A.F.; Yusoh M.A.T.M.; Hairuddin M.A.; Ashar N.D.K.
End-to-end deep learning on classification of neutral-to-ground voltage in secondary distribution systems
author_facet Mahadan M.E.; Abidin A.F.; Yusoh M.A.T.M.; Hairuddin M.A.; Ashar N.D.K.
author_sort Mahadan M.E.; Abidin A.F.; Yusoh M.A.T.M.; Hairuddin M.A.; Ashar N.D.K.
title End-to-end deep learning on classification of neutral-to-ground voltage in secondary distribution systems
title_short End-to-end deep learning on classification of neutral-to-ground voltage in secondary distribution systems
title_full End-to-end deep learning on classification of neutral-to-ground voltage in secondary distribution systems
title_fullStr End-to-end deep learning on classification of neutral-to-ground voltage in secondary distribution systems
title_full_unstemmed End-to-end deep learning on classification of neutral-to-ground voltage in secondary distribution systems
title_sort End-to-end deep learning on classification of neutral-to-ground voltage in secondary distribution systems
publishDate 2024
container_title e-Prime - Advances in Electrical Engineering, Electronics and Energy
container_volume 10
container_issue
doi_str_mv 10.1016/j.prime.2024.100795
url https://www.scopus.com/inward/record.uri?eid=2-s2.0-85205468209&doi=10.1016%2fj.prime.2024.100795&partnerID=40&md5=f2133056531d516465b8b8403a9b5ea3
description Neutral-to-ground voltage (NTGV) abnormalities in secondary distribution systems (SDS) pose significant power quality (PQ) challenges, including safety hazards, power losses, and equipment damage. Despite their importance, these abnormalities remain relatively understudied. Accurate classification of NTGV events is crucial for effective mitigation strategies. Existing research primarily relies on machine learning (ML) models trained on manually extracted features from simulated or real-world signals. This paper introduces a novel end-to-end deep learning approach that leverages Gate Recurrent Units (GRU) to bypass manual feature extraction, directly utilizing real-world signals from three NTGV event categories: ground fault, lightning strike, and normal conditions. This is first time that GRU has been used for NTGV classification using raw data. The model's generalizability is assessed through 5-fold cross-validation. A comparative analysis with baseline models and traditional ML techniques demonstrates the proposed model's superior performance and computational efficiency due to its ability to directly process raw data. © 2024
publisher Elsevier Ltd
issn 27726711
language English
format Article
accesstype All Open Access; Gold Open Access
record_format scopus
collection Scopus
_version_ 1814778496566689792