An Unsupervised Learning Framework for Event Detection, Type Identification and Localization Using PMUs Without Any Historical Labels

Haoran Li, Yang Weng, Evangelos Farantatos, Mahendra Patel

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

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.

Original languageEnglish (US)
Title of host publication2019 IEEE Power and Energy Society General Meeting, PESGM 2019
PublisherIEEE Computer Society
ISBN (Electronic)9781728119816
DOIs
StatePublished - Aug 2019
Event2019 IEEE Power and Energy Society General Meeting, PESGM 2019 - Atlanta, United States
Duration: Aug 4 2019Aug 8 2019

Publication series

NameIEEE Power and Energy Society General Meeting
Volume2019-August
ISSN (Print)1944-9925
ISSN (Electronic)1944-9933

Conference

Conference2019 IEEE Power and Energy Society General Meeting, PESGM 2019
CountryUnited States
CityAtlanta
Period8/4/198/8/19

    Fingerprint

Keywords

  • change point detection
  • Event identification
  • hierarchical clustering
  • phasor measurement unit
  • unsupervised learning

ASJC Scopus subject areas

  • Energy Engineering and Power Technology
  • Nuclear Energy and Engineering
  • Renewable Energy, Sustainability and the Environment
  • Electrical and Electronic Engineering

Cite this

Li, H., Weng, Y., Farantatos, E., & Patel, M. (2019). An Unsupervised Learning Framework for Event Detection, Type Identification and Localization Using PMUs Without Any Historical Labels. In 2019 IEEE Power and Energy Society General Meeting, PESGM 2019 [8973580] (IEEE Power and Energy Society General Meeting; Vol. 2019-August). IEEE Computer Society. https://doi.org/10.1109/PESGM40551.2019.8973580