TY - JOUR
T1 - Fault diagnosis in low voltage smart distribution grids using gradient boosting trees
AU - Sapountzoglou, Nikolaos
AU - Lago, Jesus
AU - Raison, Bertrand
PY - 2020
Y1 - 2020
N2 - In this paper, a gradient boosting tree model is proposed to detect, identify and localize single-phase-to-ground and three-phase faults in low voltage (LV) smart distribution grids. The proposed method is based on gradient boosting trees and considers branch-independent input features to be generalizable and applicable to different grid topologies. Particularly, as it is shown, the method can be estimated in a specific grid topology and be employed in a different one. To test the algorithm, the method is evaluated in a simulated real LV distribution grid of Portugal. In this case study, different fault resistances, fault locations and hours of the day are considered. In detail, the algorithm is evaluated at eighteen fault resistance values between 0.1 and 1000 Ω; similarly, nine fault locations are considered within each one of the 32 sectors of the grid and the faults are simulated across different hours of a day. The developed algorithm showed promising results in both out-of-sample branch and fault resistance data especially for fault detection, demonstrating a maximum fault detection error of 0.72%.
AB - In this paper, a gradient boosting tree model is proposed to detect, identify and localize single-phase-to-ground and three-phase faults in low voltage (LV) smart distribution grids. The proposed method is based on gradient boosting trees and considers branch-independent input features to be generalizable and applicable to different grid topologies. Particularly, as it is shown, the method can be estimated in a specific grid topology and be employed in a different one. To test the algorithm, the method is evaluated in a simulated real LV distribution grid of Portugal. In this case study, different fault resistances, fault locations and hours of the day are considered. In detail, the algorithm is evaluated at eighteen fault resistance values between 0.1 and 1000 Ω; similarly, nine fault locations are considered within each one of the 32 sectors of the grid and the faults are simulated across different hours of a day. The developed algorithm showed promising results in both out-of-sample branch and fault resistance data especially for fault detection, demonstrating a maximum fault detection error of 0.72%.
KW - Fault detection
KW - Fault diagnosis
KW - Fault identification
KW - Gradient boosting trees
KW - Low voltage distribution system
KW - Machine learning
UR - http://www.scopus.com/inward/record.url?scp=85079089193&partnerID=8YFLogxK
U2 - 10.1016/j.epsr.2020.106254
DO - 10.1016/j.epsr.2020.106254
M3 - Article
AN - SCOPUS:85079089193
SN - 0378-7796
VL - 182
JO - Electric Power Systems Research
JF - Electric Power Systems Research
M1 - 106254
ER -