An Approach Utilizing Converters for Locating Faults in LV Distribution Grids

Sami Pitkäniemi; Mikko Routimo; Jarno Kukkola; Ville Pirsto; Edris Pouresmaeil

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 proceeding › Conference article in proceedings › Scientific › peer-review

96 Downloads (Pure)

Abstract

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 language	English
Title of host publication	Proceedings of the 23rd European Conference on Power Electronics and Applications, EPE’21 ECCE Europe
Publisher	IEEE
Number of pages	10
ISBN (Electronic)	978-9-0758-1537-5
ISBN (Print)	978-1-6654-3384-6
Publication status	Published - 25 Oct 2021
MoE publication type	A4 Conference publication
Event	European Conference on Power Electronics and Applications - Virtual, online, Ghent, Belgium Duration: 6 Sept 2021 → 10 Sept 2021 Conference number: 23 http://www.epe2021.com/

Conference

Conference	European Conference on Power Electronics and Applications
Abbreviated title	EPE-ECCE Europe
Country/Territory	Belgium
City	Ghent
Period	06/09/2021 → 10/09/2021
Internet address	http://www.epe2021.com/

Keywords

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

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

Paper_finalAccepted author manuscript, 1.09 MB

https://ieeexplore.ieee.org/document/9570488

Cite this

@inproceedings{b1a140098eac4cf8b715ce6fa82c1973,

title = "An Approach Utilizing Converters for Locating Faults in LV Distribution Grids",

abstract = "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.",

keywords = "Artificial Intelligence, Distributed generation, Faults, grid-connected converter, Impedance measurement, Machine learning, Power transmission, Smart grids",

author = "Sami Pitk{\"a}niemi and Mikko Routimo and Jarno Kukkola and Ville Pirsto and Edris Pouresmaeil",

year = "2021",

month = oct,

day = "25",

language = "English",

isbn = "978-1-6654-3384-6",

booktitle = "Proceedings of the 23rd European Conference on Power Electronics and Applications, EPE{\textquoteright}21 ECCE Europe",

publisher = "IEEE",

address = "United States",

note = "European Conference on Power Electronics and Applications, EPE-ECCE Europe ; Conference date: 06-09-2021 Through 10-09-2021",

url = "http://www.epe2021.com/",

}

Pitkäniemi, S, Routimo, M, Kukkola, J, Pirsto, V & Pouresmaeil, E 2021, An Approach Utilizing Converters for Locating Faults in LV Distribution Grids. in Proceedings of the 23rd European Conference on Power Electronics and Applications, EPE’21 ECCE Europe. IEEE, European Conference on Power Electronics and Applications, Ghent, Belgium, 06/09/2021. <https://ieeexplore.ieee.org/document/9570488>

An Approach Utilizing Converters for Locating Faults in LV Distribution Grids. / Pitkäniemi, Sami; Routimo, Mikko; Kukkola, Jarno et al.
Proceedings of the 23rd European Conference on Power Electronics and Applications, EPE’21 ECCE Europe. IEEE, 2021.

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - An Approach Utilizing Converters for Locating Faults in LV Distribution Grids

AU - Pitkäniemi, Sami

AU - Routimo, Mikko

AU - Kukkola, Jarno

AU - Pirsto, Ville

AU - Pouresmaeil, Edris

N1 - Conference code: 23

PY - 2021/10/25

Y1 - 2021/10/25

N2 - 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.

AB - 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.

KW - Artificial Intelligence

KW - Distributed generation

KW - Faults

KW - grid-connected converter

KW - Impedance measurement

KW - Machine learning

KW - Power transmission

KW - Smart grids

M3 - Conference article in proceedings

SN - 978-1-6654-3384-6

BT - Proceedings of the 23rd European Conference on Power Electronics and Applications, EPE’21 ECCE Europe

PB - IEEE

T2 - European Conference on Power Electronics and Applications

Y2 - 6 September 2021 through 10 September 2021

ER -

An Approach Utilizing Converters for Locating Faults in LV Distribution Grids

Abstract

Conference

Keywords

UN SDGs

Access to Document

Fingerprint

Cite this