Discrimination of high impedance fault in microgrid power network using semi-supervised machine learning algorithm
This work proposes a semi-supervised classification approach for discriminating high-impedance (HI) faults and other transients in a photovoltaic (PV) interconnected microgrid (MG) network. The suggested classifier combines unsupervised K-means clustering with the supervised multi-layer perceptron n...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-01-01
|
| Series: | Ain Shams Engineering Journal |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2090447924005689 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841526256370188288 |
|---|---|
| author | Arangarajan Vinayagam S.T. Suganthi C.B. Venkatramanan Ayoob Alateeq Abdullah Alassaf Nur Fadilah Ab Aziz Mohd Helmi Mansor Saad Mekhilef |
| author_facet | Arangarajan Vinayagam S.T. Suganthi C.B. Venkatramanan Ayoob Alateeq Abdullah Alassaf Nur Fadilah Ab Aziz Mohd Helmi Mansor Saad Mekhilef |
| author_sort | Arangarajan Vinayagam |
| collection | DOAJ |
| description | This work proposes a semi-supervised classification approach for discriminating high-impedance (HI) faults and other transients in a photovoltaic (PV) interconnected microgrid (MG) network. The suggested classifier combines unsupervised K-means clustering with the supervised multi-layer perceptron neural network algorithm. The K-means clustering technique is utilized in the first phase to detect and remove irrelevant instances from multiple events in the data set. To obtain the final predictions of targeted labels, clustered cases from the first phase are utilized to learn the multi-layer perceptron neural network classifier in the next phase. The suggested method outperforms stand-alone classifiers (K-means clustering and multi-layer perceptron) by providing enhanced accuracy and success rate of discriminating HI fault under standard test conditions and weather intermittency of PV. Furthermore, the results of the performance study clearly show that the suggested model is more resilient and offers superior performance than the stand-alone classifiers under the standard test condition and uncertainty of PV in MG networks. |
| format | Article |
| id | doaj-art-2d93662726bc44b5ab9fe1bf38c2eaff |
| institution | Kabale University |
| issn | 2090-4479 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Ain Shams Engineering Journal |
| spelling | doaj-art-2d93662726bc44b5ab9fe1bf38c2eaff2025-01-17T04:49:20ZengElsevierAin Shams Engineering Journal2090-44792025-01-01161103187Discrimination of high impedance fault in microgrid power network using semi-supervised machine learning algorithmArangarajan Vinayagam0S.T. Suganthi1C.B. Venkatramanan2Ayoob Alateeq3Abdullah Alassaf4Nur Fadilah Ab Aziz5Mohd Helmi Mansor6Saad Mekhilef7Institute of Power Engineering, Universiti Tenaga Nasional, Jalan IKRAM-UNITEN, Kajang, Selangor 43000, Malaysia; Department of Electrical and Electronics Engineering, New Horizon College of Engineering, Bangaluru, India; Corresponding author at: Institute of Power Engineering, Universiti Tenaga Nasional, Jalan IKRAM-UNITEN, Kajang, Selangor 43000, Malaysia.Department of Electrical and Electronics Engineering, Kumaraguru College of Technology, Coimbatore, IndiaDepartment of Electrical Engineering, Sona College of Technology, Salem, IndiaDepartment of Electrical Engineering, College of Engineering, University of Hail, Hail 2240, Saudi ArabiaDepartment of Electrical Engineering, College of Engineering, University of Hail, Hail 2240, Saudi ArabiaInstitute of Power Engineering, Universiti Tenaga Nasional, Jalan IKRAM-UNITEN, Kajang, Selangor 43000, MalaysiaInstitute of Power Engineering, Universiti Tenaga Nasional, Jalan IKRAM-UNITEN, Kajang, Selangor 43000, MalaysiaSchool of Science, Computing and Engineering Technologies, Swinburne University of Technology, Melbourne, VIC 3122, AustraliaThis work proposes a semi-supervised classification approach for discriminating high-impedance (HI) faults and other transients in a photovoltaic (PV) interconnected microgrid (MG) network. The suggested classifier combines unsupervised K-means clustering with the supervised multi-layer perceptron neural network algorithm. The K-means clustering technique is utilized in the first phase to detect and remove irrelevant instances from multiple events in the data set. To obtain the final predictions of targeted labels, clustered cases from the first phase are utilized to learn the multi-layer perceptron neural network classifier in the next phase. The suggested method outperforms stand-alone classifiers (K-means clustering and multi-layer perceptron) by providing enhanced accuracy and success rate of discriminating HI fault under standard test conditions and weather intermittency of PV. Furthermore, the results of the performance study clearly show that the suggested model is more resilient and offers superior performance than the stand-alone classifiers under the standard test condition and uncertainty of PV in MG networks.http://www.sciencedirect.com/science/article/pii/S2090447924005689PhotovoltaicHigh impedance faultK-means clusteringMulti-layer perceptronMicrogridEnergy |
| spellingShingle | Arangarajan Vinayagam S.T. Suganthi C.B. Venkatramanan Ayoob Alateeq Abdullah Alassaf Nur Fadilah Ab Aziz Mohd Helmi Mansor Saad Mekhilef Discrimination of high impedance fault in microgrid power network using semi-supervised machine learning algorithm Ain Shams Engineering Journal Photovoltaic High impedance fault K-means clustering Multi-layer perceptron Microgrid Energy |
| title | Discrimination of high impedance fault in microgrid power network using semi-supervised machine learning algorithm |
| title_full | Discrimination of high impedance fault in microgrid power network using semi-supervised machine learning algorithm |
| title_fullStr | Discrimination of high impedance fault in microgrid power network using semi-supervised machine learning algorithm |
| title_full_unstemmed | Discrimination of high impedance fault in microgrid power network using semi-supervised machine learning algorithm |
| title_short | Discrimination of high impedance fault in microgrid power network using semi-supervised machine learning algorithm |
| title_sort | discrimination of high impedance fault in microgrid power network using semi supervised machine learning algorithm |
| topic | Photovoltaic High impedance fault K-means clustering Multi-layer perceptron Microgrid Energy |
| url | http://www.sciencedirect.com/science/article/pii/S2090447924005689 |
| work_keys_str_mv | AT arangarajanvinayagam discriminationofhighimpedancefaultinmicrogridpowernetworkusingsemisupervisedmachinelearningalgorithm AT stsuganthi discriminationofhighimpedancefaultinmicrogridpowernetworkusingsemisupervisedmachinelearningalgorithm AT cbvenkatramanan discriminationofhighimpedancefaultinmicrogridpowernetworkusingsemisupervisedmachinelearningalgorithm AT ayoobalateeq discriminationofhighimpedancefaultinmicrogridpowernetworkusingsemisupervisedmachinelearningalgorithm AT abdullahalassaf discriminationofhighimpedancefaultinmicrogridpowernetworkusingsemisupervisedmachinelearningalgorithm AT nurfadilahabaziz discriminationofhighimpedancefaultinmicrogridpowernetworkusingsemisupervisedmachinelearningalgorithm AT mohdhelmimansor discriminationofhighimpedancefaultinmicrogridpowernetworkusingsemisupervisedmachinelearningalgorithm AT saadmekhilef discriminationofhighimpedancefaultinmicrogridpowernetworkusingsemisupervisedmachinelearningalgorithm |