TY - JOUR
T1 - Enhance High Impedance Fault Detection and Location Accuracy via \mu -PMUs
AU - Cui, Qiushi
AU - Weng, Yang
N1 - Funding Information:
Manuscript received October 23, 2018; revised March 6, 2019 and May 27, 2019; accepted June 30, 2019. Date of publication July 3, 2019; date of current version December 23, 2019. This work was supported by the National Science Foundation (NSF) under Grant 1807142. Paper no. TSG-01587-2018. (Corresponding author: Yang Weng.) The authors are with the School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ 85281 USA (e-mail: qiushi.cui@asu.edu; yang.weng@asu.edu).
Funding Information:
This work was supported by the National Science Foundation (NSF) under Grant 1807142. Paper no. TSG-01587-2018.
Publisher Copyright:
© 2010-2012 IEEE.
PY - 2020/1
Y1 - 2020/1
N2 - The high impedance fault (HIF) has random, irregular, and unsymmetrical characteristics, making such a fault difficult to detect in distribution grids via conventional relay measurements with relatively low resolution and accuracy. This paper proposes a stochastic HIF monitoring and location scheme using high-resolution time-synchronized data in \mu -PMUs for distribution network protection. Specifically, we systematically design a process based on feature selections, semi-supervised learning (SSL), and probabilistic learning for fault detection and location. For example, a wrapper method is proposed to leverage output data in feature selection to avoid overfitting and reduce communication demand. To utilize unlabeled data and quantify uncertainties, an SSL-based method is proposed using the information theory for fault detection. For location, a probabilistic analysis is proposed via moving window total least square based on the probability distribution of the fault impedance. For numerical validation, we set up an experiment platform based on the real-time simulator, so that the real-time property of \mu -PMU can be examined. Such experiment shows enhanced HIF detection and location, when compared to the traditional methods.
AB - The high impedance fault (HIF) has random, irregular, and unsymmetrical characteristics, making such a fault difficult to detect in distribution grids via conventional relay measurements with relatively low resolution and accuracy. This paper proposes a stochastic HIF monitoring and location scheme using high-resolution time-synchronized data in \mu -PMUs for distribution network protection. Specifically, we systematically design a process based on feature selections, semi-supervised learning (SSL), and probabilistic learning for fault detection and location. For example, a wrapper method is proposed to leverage output data in feature selection to avoid overfitting and reduce communication demand. To utilize unlabeled data and quantify uncertainties, an SSL-based method is proposed using the information theory for fault detection. For location, a probabilistic analysis is proposed via moving window total least square based on the probability distribution of the fault impedance. For numerical validation, we set up an experiment platform based on the real-time simulator, so that the real-time property of \mu -PMU can be examined. Such experiment shows enhanced HIF detection and location, when compared to the traditional methods.
KW - High impedance fault
KW - fault location
KW - semi-supervised learning
KW - μ-PMUs
UR - http://www.scopus.com/inward/record.url?scp=85068567146&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85068567146&partnerID=8YFLogxK
U2 - 10.1109/TSG.2019.2926668
DO - 10.1109/TSG.2019.2926668
M3 - Article
AN - SCOPUS:85068567146
SN - 1949-3053
VL - 11
SP - 797
EP - 809
JO - IEEE Transactions on Smart Grid
JF - IEEE Transactions on Smart Grid
IS - 1
M1 - 8755317
ER -