A Deep GMDH Neural-Network-Based Robust Fault Detection Method for Active Distribution Networks

Basit Öğe Kaydı
dc.authoridChen, Zhe/0000-0002-2919-4481
dc.authoridCELIK, Ozgur/0000-0002-7683-2415
dc.authoridGuerrero, Josep/0000-0001-5236-4592
dc.authoridVasquez, Juan C./0000-0001-6332-385X
dc.authoridLashab, Abderezak/0000-0002-4891-873X
dc.authoridSahebkar Farkhani, Jalal/0000-0002-6788-7588
dc.contributor.authorCelik, Ozgur
dc.contributor.authorFarkhani, Jalal Sahebkar
dc.contributor.authorLashab, Abderezak
dc.contributor.authorGuerrero, Josep M.
dc.contributor.authorVasquez, Juan C.
dc.contributor.authorChen, Zhe
dc.contributor.authorBak, Claus Leth
dc.date.accessioned2025-01-06T17:38:11Z
dc.date.available2025-01-06T17:38:11Z
dc.date.issued2023
dc.description.abstractThe increasing penetration of distributed generation (DG) to power distribution networks mainly induces weaknesses in the sensitivity and selectivity of protection systems. In this manner, conventional protection systems often fail to protect active distribution networks (ADN) in the case of short-circuit faults. To overcome these challenges, the accurate detection of faults in a reasonable fraction of time appears as a critical issue in distribution networks. Machine learning techniques are capable of generating efficient analytical expressions that can be strong candidates in terms of reliable and robust fault detection for several operating scenarios of ADNs. This paper proposes a deep group method of data handling (GMDH) neural network based on a non-pilot protection method for the protection of an ADN. The developed method is independent of the DG capacity and achieves accurate fault detection under load variations, disturbances, and different high-impedance faults (HIFs). To verify the improvements, a test system based on a real distribution network that includes three generators with a capacity of 6 MW is utilized. The extensive simulations of the power network are performed using DIgSILENT Power Factory and MATLAB software. The obtained results reveal that a mean absolute percentage error (MAPE) of 3.51% for the GMDH-network-based protection system is accomplished thanks to formulation via optimized algorithms, without requiring the utilization of any feature selection techniques. The proposed method has a high-speed operation of around 20 ms for the detection of faults, while the conventional OC relay performance is in the blinding mode in the worst situations for faults with HIFs.
dc.description.sponsorshipScientific and Technological Research Council of Turkey (TUBITAK); Scientific and Technological Research Council of Turkey BIDEB 2219 International Doctoral Research Fellowship Programme [1059B192100759]; VILLUM FONDEN [25920]
dc.description.sponsorshipThis work was supported by The Scientific and Technological Research Council of Turkey BIDEB 2219 International Doctoral Research Fellowship Programme reference number: 1059B192100759.Josep M. Guerrero and Abderezak Lashab are funded by VILLUM FONDEN under the VILLUM Investigator Grant (25920): Center for Research on Microgrids (CROM)
dc.identifier.doi10.3390/en16196867
dc.identifier.issn1996-1073
dc.identifier.issue19
dc.identifier.scopus2-s2.0-85174032046
dc.identifier.scopusqualityQ1
dc.identifier.urihttps://doi.org/10.3390/en16196867
dc.identifier.urihttps://hdl.handle.net/20.500.14669/2512
dc.identifier.volume16
dc.identifier.wosWOS:001084219800001
dc.identifier.wosqualityQ3
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherMdpi
dc.relation.ispartofEnergies
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.snmzKA_20241211
dc.subjectGMDH-based fault detection
dc.subjectconventional protection scheme
dc.subjectactive distribution networks
dc.subjectblinding areas
dc.titleA Deep GMDH Neural-Network-Based Robust Fault Detection Method for Active Distribution Networks
dc.typeArticle

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu