An Approach Utilizing Converters for Locating Faults in LV Distribution Grids

Sami Pitkäniemi, Mikko Routimo*, Jarno Kukkola, Ville Pirsto, Edris Pouresmaeil

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

40 Downloads (Pure)


This paper proposes an approach for locating faults in a distribution grid by utilizing data measured and gathered by distributed converters. The data, comprising grid voltages and impedances from multiple locations, is processed using multinomial logistic regression, a machine learning algorithm, to classify a fault location in the grid. The algorithm is first trained with simulation data, followed by evaluation of its predictive performance using a set of test data previously unseen by the algorithm. The fault location accuracy of the proposed approach is found resonable and encourages further studies of the unused potential in the converters.
Original languageEnglish
Title of host publicationProceedings of the 23rd European Conference on Power Electronics and Applications, EPE’21 ECCE Europe
Number of pages10
ISBN (Electronic)978-9-0758-1537-5
ISBN (Print)978-1-6654-3384-6
Publication statusPublished - 25 Oct 2021
MoE publication typeA4 Article in a conference publication
EventEuropean Conference on Power Electronics and Applications - Virtual, online, Ghent, Belgium
Duration: 6 Sept 202110 Sept 2021
Conference number: 23


ConferenceEuropean Conference on Power Electronics and Applications
Abbreviated titleEPE-ECCE Europe
Internet address


  • Artificial Intelligence
  • Distributed generation
  • Faults
  • grid-connected converter
  • Impedance measurement
  • Machine learning
  • Power transmission
  • Smart grids


Dive into the research topics of 'An Approach Utilizing Converters for Locating Faults in LV Distribution Grids'. Together they form a unique fingerprint.

Cite this