Accurate detection of critical LLFs and LGFs in PV arrays based on deep reinforcement learning using proximal policy optimization (PPO)

Critical line-to-line faults (LLFs) and line-to-ground faults (LGFs) in photovoltaic (PV) systems are the most difficult faults to detect not only by conventional protection devices, but also modern fault detection schemes. The difficulty occurs due to critical mismatch levels and/or high fault impe...

Full description

Saved in:
Bibliographic Details
Main Authors: Sherko Salehpour, Aref Eskandari, Amir Nedaei, Mohammad Gholami, Mohammadreza Aghaei
Format: Article
Language:English
Published: Elsevier 2025-07-01
Series:International Journal of Electrical Power & Energy Systems
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S0142061525002121
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849321728277217280
author Sherko Salehpour
Aref Eskandari
Amir Nedaei
Mohammad Gholami
Mohammadreza Aghaei
author_facet Sherko Salehpour
Aref Eskandari
Amir Nedaei
Mohammad Gholami
Mohammadreza Aghaei
author_sort Sherko Salehpour
collection DOAJ
description Critical line-to-line faults (LLFs) and line-to-ground faults (LGFs) in photovoltaic (PV) systems are the most difficult faults to detect not only by conventional protection devices, but also modern fault detection schemes. The difficulty occurs due to critical mismatch levels and/or high fault impedance values which result in LLFs and LGFs remain undetected thus damaging the PV components, affecting system stability, reliability, and efficiency, and even leading to catastrophic fire hazards. However, challenges persist even in recent studies, including the need for a massive training dataset, disregard of fault severity assessment, and insufficient model accuracy. To address these challenges, the present paper proposes a deep reinforcement learning (DRL)-based model to detect, classify, and assess the severity of all and specifically critical LLFs and LGFs in PV arrays using the proximal policy optimization (PPO) algorithm. Additionally, to carry out the dataset dimensionality reduction, thus simplifying the training process, a two-stage feature engineering process has been implemented, including a feature importance finding stage using the permutation technique and a feature selection stage. To implement the proposed model and verify its capability in real-life condition, a laboratory PV system has been carefully designed. The results of the real-world experiment shows that the proposed model is able to detect LLFs and LGFs, under various environmental (temperature and irradiance), and electrical (mismatch and impedance) conditions with outstanding 100% of accuracy in the test process, using only a small training dataset.
format Article
id doaj-art-84730f9e0e8a48f4a3b50663ebacdae3
institution Kabale University
issn 0142-0615
language English
publishDate 2025-07-01
publisher Elsevier
record_format Article
series International Journal of Electrical Power & Energy Systems
spelling doaj-art-84730f9e0e8a48f4a3b50663ebacdae32025-08-20T03:49:41ZengElsevierInternational Journal of Electrical Power & Energy Systems0142-06152025-07-0116811066110.1016/j.ijepes.2025.110661Accurate detection of critical LLFs and LGFs in PV arrays based on deep reinforcement learning using proximal policy optimization (PPO)Sherko Salehpour0Aref Eskandari1Amir Nedaei2Mohammad Gholami3Mohammadreza Aghaei4Department of Electrical Engineering, Amirkabir University of Technology (AUT), Tehran, IranDepartment of Electrical Engineering, Iran University of Science and Technology (IUST), Tehran, Iran; Corresponding author at: Department of Ocean Operations and Civil Engineering, Norwegian University of Science and Technology (NTNU), Norway (M. Aghaei); Department of Electrical Engineering, Iran University of Science and Technology (IUST), Iran (A. Eskandari).Department of Electrical Engineering, Amirkabir University of Technology (AUT), Tehran, IranDepartment of Electrical and Computer Engineering, University of Science and Technology of Mazandaran, Behshahr, IranDepartment of Ocean Operations and Civil Engineering, Norwegian University of Science and Technology (NTNU), Norway; Department of Sustainable Systems Engineering (INATECH), University of Freiburg, Freiburg, Germany; Corresponding author at: Department of Ocean Operations and Civil Engineering, Norwegian University of Science and Technology (NTNU), Norway (M. Aghaei); Department of Electrical Engineering, Iran University of Science and Technology (IUST), Iran (A. Eskandari).Critical line-to-line faults (LLFs) and line-to-ground faults (LGFs) in photovoltaic (PV) systems are the most difficult faults to detect not only by conventional protection devices, but also modern fault detection schemes. The difficulty occurs due to critical mismatch levels and/or high fault impedance values which result in LLFs and LGFs remain undetected thus damaging the PV components, affecting system stability, reliability, and efficiency, and even leading to catastrophic fire hazards. However, challenges persist even in recent studies, including the need for a massive training dataset, disregard of fault severity assessment, and insufficient model accuracy. To address these challenges, the present paper proposes a deep reinforcement learning (DRL)-based model to detect, classify, and assess the severity of all and specifically critical LLFs and LGFs in PV arrays using the proximal policy optimization (PPO) algorithm. Additionally, to carry out the dataset dimensionality reduction, thus simplifying the training process, a two-stage feature engineering process has been implemented, including a feature importance finding stage using the permutation technique and a feature selection stage. To implement the proposed model and verify its capability in real-life condition, a laboratory PV system has been carefully designed. The results of the real-world experiment shows that the proposed model is able to detect LLFs and LGFs, under various environmental (temperature and irradiance), and electrical (mismatch and impedance) conditions with outstanding 100% of accuracy in the test process, using only a small training dataset.http://www.sciencedirect.com/science/article/pii/S0142061525002121Photovoltaic (PV) systemFault detection and diagnosis (FDD)Deep reinforcement learning (DRL)Proximal policy optimization (PPO)Feature engineeringPermutation feature importance technique
spellingShingle Sherko Salehpour
Aref Eskandari
Amir Nedaei
Mohammad Gholami
Mohammadreza Aghaei
Accurate detection of critical LLFs and LGFs in PV arrays based on deep reinforcement learning using proximal policy optimization (PPO)
International Journal of Electrical Power & Energy Systems
Photovoltaic (PV) system
Fault detection and diagnosis (FDD)
Deep reinforcement learning (DRL)
Proximal policy optimization (PPO)
Feature engineering
Permutation feature importance technique
title Accurate detection of critical LLFs and LGFs in PV arrays based on deep reinforcement learning using proximal policy optimization (PPO)
title_full Accurate detection of critical LLFs and LGFs in PV arrays based on deep reinforcement learning using proximal policy optimization (PPO)
title_fullStr Accurate detection of critical LLFs and LGFs in PV arrays based on deep reinforcement learning using proximal policy optimization (PPO)
title_full_unstemmed Accurate detection of critical LLFs and LGFs in PV arrays based on deep reinforcement learning using proximal policy optimization (PPO)
title_short Accurate detection of critical LLFs and LGFs in PV arrays based on deep reinforcement learning using proximal policy optimization (PPO)
title_sort accurate detection of critical llfs and lgfs in pv arrays based on deep reinforcement learning using proximal policy optimization ppo
topic Photovoltaic (PV) system
Fault detection and diagnosis (FDD)
Deep reinforcement learning (DRL)
Proximal policy optimization (PPO)
Feature engineering
Permutation feature importance technique
url http://www.sciencedirect.com/science/article/pii/S0142061525002121
work_keys_str_mv AT sherkosalehpour accuratedetectionofcriticalllfsandlgfsinpvarraysbasedondeepreinforcementlearningusingproximalpolicyoptimizationppo
AT arefeskandari accuratedetectionofcriticalllfsandlgfsinpvarraysbasedondeepreinforcementlearningusingproximalpolicyoptimizationppo
AT amirnedaei accuratedetectionofcriticalllfsandlgfsinpvarraysbasedondeepreinforcementlearningusingproximalpolicyoptimizationppo
AT mohammadgholami accuratedetectionofcriticalllfsandlgfsinpvarraysbasedondeepreinforcementlearningusingproximalpolicyoptimizationppo
AT mohammadrezaaghaei accuratedetectionofcriticalllfsandlgfsinpvarraysbasedondeepreinforcementlearningusingproximalpolicyoptimizationppo