Umeå University's logo

umu.sePublikasjoner
Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Most influential feature form for supervised learning in voltage sag source localization
Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för tillämpad fysik och elektronik.ORCID-id: 0000-0001-8660-5569
Faculty of Electrical Engineering and Computer Science, University of Maribor, Maribor, 2000, Slovenia.
Universidade Federal do Rio Grande do Sul, Osvaldo Aranha, 99, RS, Porto Alegre, 90035-190, Brazil.
Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för tillämpad fysik och elektronik.ORCID-id: 0000-0003-2960-3094
2024 (engelsk)Inngår i: Engineering applications of artificial intelligence, ISSN 0952-1976, E-ISSN 1873-6769, Vol. 133, nr Part D, artikkel-id 108331Artikkel i tidsskrift (Fagfellevurdert) Published
Abstract [en]

The paper investigates the application of machine learning (ML) for voltage sag source localization (VSSL) in electrical power systems. To overcome feature-selection challenges for traditional ML methods and provide more meaningful sequential features for deep learning methods, the paper proposes three time-sample-based feature forms, and evaluates an existing feature form. The effectiveness of these feature forms is assessed using k-means clustering with k = 2 referred to as downstream and upstream classes, according to the direction of voltage sag origins. Through extensive voltage sag simulations, including noises in a regional electrical power network, k-means identifies a sequence involving the multiplication of positive-sequence current magnitude with the sine of its angle as the most prominent feature form. The study develops further traditional ML methods such as decision trees (DT), support vector machine (SVM), random forest (RF), k-nearest neighbor (KNN), an ensemble learning (EL), and a designed one-dimensional convolutional neural network (1D-CNN). The results found that the combination of 1D-CNN or SVM with the most prominent feature achieved the highest accuracies of 99.37% and 99.13%, respectively, with acceptable/fast prediction times, enhancing VSSL. The exceptional performance of the CNN was also approved by field measurements in a real power network. However, selecting the best ML methods for deployment requires a trade-off between accuracy and real-time implementation requirements. The research findings benefit network operators, large factory owners, and renewable energy park producers. They enable preventive maintenance, reduce equipment downtime/damage in industry and electrical power systems, mitigate financial losses, and facilitate the assignment of power-quality penalties to responsible parties.

sted, utgiver, år, opplag, sider
Elsevier, 2024. Vol. 133, nr Part D, artikkel-id 108331
Emneord [en]
Voltage sag (dip), Source localization, Supervised and unsupervised learning, Convolutional neural network, Time-sample-based features
HSV kategori
Identifikatorer
URN: urn:nbn:se:umu:diva-223198DOI: 10.1016/j.engappai.2024.108331Scopus ID: 2-s2.0-85189522853OAI: oai:DiVA.org:umu-223198DiVA, id: diva2:1850779
Forskningsfinansiär
The Kempe Foundations, JCK22-0025Tilgjengelig fra: 2024-04-11 Laget: 2024-04-11 Sist oppdatert: 2024-04-15bibliografisk kontrollert

Open Access i DiVA

fulltext(16327 kB)45 nedlastinger
Filinformasjon
Fil FULLTEXT01.pdfFilstørrelse 16327 kBChecksum SHA-512
8f9ef31c74aabf38b209b6f6ca6a431abd2645a633244406dca20f6274954d5b49dbf210d6de61c24445f2dfa53916c7940ae25e31139f05018d43ce9fb1a66c
Type fulltextMimetype application/pdf

Andre lenker

Forlagets fulltekstScopus

Person

Mohammadi, YounesKhodadad, Davood

Søk i DiVA

Av forfatter/redaktør
Mohammadi, YounesKhodadad, Davood
Av organisasjonen
I samme tidsskrift
Engineering applications of artificial intelligence

Søk utenfor DiVA

GoogleGoogle Scholar
Totalt: 45 nedlastinger
Antall nedlastinger er summen av alle nedlastinger av alle fulltekster. Det kan for eksempel være tidligere versjoner som er ikke lenger tilgjengelige

doi
urn-nbn

Altmetric

doi
urn-nbn
Totalt: 213 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf