TY - GEN
T1 - An Unsupervised Learning Framework for Event Detection, Type Identification and Localization Using PMUs Without Any Historical Labels
AU - Li, Haoran
AU - Weng, Yang
AU - Farantatos, Evangelos
AU - Patel, Mahendra
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/8
Y1 - 2019/8
N2 - The power system requires new monitoring and controls due to changes both at the generation side as well as the load side. Synchrophasor technology with synchronized and high-resolution measurements provided by Phasor Measurement Units (PMUs) has been recognized as a key contributing technology for advanced situational awareness, including event identification, where the application of machine learning techniques is a hot topic recently. However, recent methods focus on supervised learning techniques that require event records, which may be unavailable due to labeling cost. Even if labels exist, the uneven labeled data may cause biased learning models. To address these challenges, an unsupervised learning approach is proposed for conducting fast event identification. Specifically, a highly sensitive and accurate change-point detection method is firstly introduced for finding events via data distribution changes. After detection, event type identification is achieved via a two-stage information filtering. In stage 1, we use cluster number in principal component analysis (PCA) to split the event types. In stage 2, we narrow down the type by evaluating cluster compactness for measuring event severity. Finally, we solve the event localization problem based on a hierarchical clustering to group PMUs with significant changes across change points. Numerical results show fast and robust performances of the proposed methods for different events at different locations.
AB - The power system requires new monitoring and controls due to changes both at the generation side as well as the load side. Synchrophasor technology with synchronized and high-resolution measurements provided by Phasor Measurement Units (PMUs) has been recognized as a key contributing technology for advanced situational awareness, including event identification, where the application of machine learning techniques is a hot topic recently. However, recent methods focus on supervised learning techniques that require event records, which may be unavailable due to labeling cost. Even if labels exist, the uneven labeled data may cause biased learning models. To address these challenges, an unsupervised learning approach is proposed for conducting fast event identification. Specifically, a highly sensitive and accurate change-point detection method is firstly introduced for finding events via data distribution changes. After detection, event type identification is achieved via a two-stage information filtering. In stage 1, we use cluster number in principal component analysis (PCA) to split the event types. In stage 2, we narrow down the type by evaluating cluster compactness for measuring event severity. Finally, we solve the event localization problem based on a hierarchical clustering to group PMUs with significant changes across change points. Numerical results show fast and robust performances of the proposed methods for different events at different locations.
KW - Event identification
KW - change point detection
KW - hierarchical clustering
KW - phasor measurement unit
KW - unsupervised learning
UR - http://www.scopus.com/inward/record.url?scp=85079062419&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85079062419&partnerID=8YFLogxK
U2 - 10.1109/PESGM40551.2019.8973580
DO - 10.1109/PESGM40551.2019.8973580
M3 - Conference contribution
AN - SCOPUS:85079062419
T3 - IEEE Power and Energy Society General Meeting
BT - 2019 IEEE Power and Energy Society General Meeting, PESGM 2019
PB - IEEE Computer Society
T2 - 2019 IEEE Power and Energy Society General Meeting, PESGM 2019
Y2 - 4 August 2019 through 8 August 2019
ER -