An Advanced Local Current-Only Protection for Microgrids: Deep-Learning-Based Approach

The integrity of protection actions in microgrids (MGs) is often compromised by varying operational conditions and contingencies. Notably, the operation of on-load tap-changers (OLTCs) can lead to the maloperation of overcurrent relays during both internal and external faults due to the altered faul...

Full description

Saved in:
Bibliographic Details
Main Authors: Amin Yazdaninejadi, Hossein Ebrahimi, Sajjad Golshannavaz
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10942361/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850272936122908672
author Amin Yazdaninejadi
Hossein Ebrahimi
Sajjad Golshannavaz
author_facet Amin Yazdaninejadi
Hossein Ebrahimi
Sajjad Golshannavaz
author_sort Amin Yazdaninejadi
collection DOAJ
description The integrity of protection actions in microgrids (MGs) is often compromised by varying operational conditions and contingencies. Notably, the operation of on-load tap-changers (OLTCs) can lead to the maloperation of overcurrent relays during both internal and external faults due to the altered fault current levels. This issue, combined with diverse operational conditions and other N-1 contingencies, further broadens the scope of undesirable operations. A deep-learning (DL) assisted fault detection method is introduced in this paper, which addresses the impact of OLTC operation on overcurrent protection in MGs under different operational scenarios. The proposed method utilizes a long short-term memory (LSTM) model to detect faults, taking into account the OLTC operation, on/off-grid status of the MG, outages of distributed generations (DGs), and capacitor bank switching. Additionally, various fault locations and resistances are incorporated into all simulated fault scenarios to enhance the training performance of the method. The ability of the LSTM model to interpret temporal dependencies in time-series signals allows the proposed method to rely solely on single-sourced current measurements at the relaying point, thereby reducing costs and improving module security. Simulation results on the low-voltage section of the IEEE 14-bus test system demonstrate the effectiveness of the proposed method in fault detection compared to existing approaches.
format Article
id doaj-art-19fb2f19514f474bbc950215fe59c9df
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-19fb2f19514f474bbc950215fe59c9df2025-08-20T01:51:39ZengIEEEIEEE Access2169-35362025-01-0113564285643810.1109/ACCESS.2025.355512310942361An Advanced Local Current-Only Protection for Microgrids: Deep-Learning-Based ApproachAmin Yazdaninejadi0https://orcid.org/0000-0003-4506-2988Hossein Ebrahimi1https://orcid.org/0000-0003-3872-0786Sajjad Golshannavaz2https://orcid.org/0000-0003-4999-8281Department of Electrical Engineering, Shahid Rajaee Teacher Training University, Tehran, IranElectrical Engineering Department, Urmia University, Urmia, IranElectrical Engineering Department, Urmia University, Urmia, IranThe integrity of protection actions in microgrids (MGs) is often compromised by varying operational conditions and contingencies. Notably, the operation of on-load tap-changers (OLTCs) can lead to the maloperation of overcurrent relays during both internal and external faults due to the altered fault current levels. This issue, combined with diverse operational conditions and other N-1 contingencies, further broadens the scope of undesirable operations. A deep-learning (DL) assisted fault detection method is introduced in this paper, which addresses the impact of OLTC operation on overcurrent protection in MGs under different operational scenarios. The proposed method utilizes a long short-term memory (LSTM) model to detect faults, taking into account the OLTC operation, on/off-grid status of the MG, outages of distributed generations (DGs), and capacitor bank switching. Additionally, various fault locations and resistances are incorporated into all simulated fault scenarios to enhance the training performance of the method. The ability of the LSTM model to interpret temporal dependencies in time-series signals allows the proposed method to rely solely on single-sourced current measurements at the relaying point, thereby reducing costs and improving module security. Simulation results on the low-voltage section of the IEEE 14-bus test system demonstrate the effectiveness of the proposed method in fault detection compared to existing approaches.https://ieeexplore.ieee.org/document/10942361/Microgrid protectionfault detection strategyoperational conditionslong short-term memory (LSTM)overcurrent relays characteristics
spellingShingle Amin Yazdaninejadi
Hossein Ebrahimi
Sajjad Golshannavaz
An Advanced Local Current-Only Protection for Microgrids: Deep-Learning-Based Approach
IEEE Access
Microgrid protection
fault detection strategy
operational conditions
long short-term memory (LSTM)
overcurrent relays characteristics
title An Advanced Local Current-Only Protection for Microgrids: Deep-Learning-Based Approach
title_full An Advanced Local Current-Only Protection for Microgrids: Deep-Learning-Based Approach
title_fullStr An Advanced Local Current-Only Protection for Microgrids: Deep-Learning-Based Approach
title_full_unstemmed An Advanced Local Current-Only Protection for Microgrids: Deep-Learning-Based Approach
title_short An Advanced Local Current-Only Protection for Microgrids: Deep-Learning-Based Approach
title_sort advanced local current only protection for microgrids deep learning based approach
topic Microgrid protection
fault detection strategy
operational conditions
long short-term memory (LSTM)
overcurrent relays characteristics
url https://ieeexplore.ieee.org/document/10942361/
work_keys_str_mv AT aminyazdaninejadi anadvancedlocalcurrentonlyprotectionformicrogridsdeeplearningbasedapproach
AT hosseinebrahimi anadvancedlocalcurrentonlyprotectionformicrogridsdeeplearningbasedapproach
AT sajjadgolshannavaz anadvancedlocalcurrentonlyprotectionformicrogridsdeeplearningbasedapproach
AT aminyazdaninejadi advancedlocalcurrentonlyprotectionformicrogridsdeeplearningbasedapproach
AT hosseinebrahimi advancedlocalcurrentonlyprotectionformicrogridsdeeplearningbasedapproach
AT sajjadgolshannavaz advancedlocalcurrentonlyprotectionformicrogridsdeeplearningbasedapproach