Online Detection of Events With Low-Quality Synchrophasor Measurements Based on $i$Forest
- 7 January 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 17 (1), 168-178
- https://doi.org/10.1109/tii.2020.2964692
Abstract
In this paper, we propose an online data-driven approach that leverages the isolation mechanism for fast event detection with low-quality data measurement. The proposed adaptive and online isolation forest (iForest)-based detection (AOIFD) method adopts a hierarchical subspace feature selection scheme to design two levels of detectors. As such, it is capable of differentiating events from low-quality data measurements, preventing false alarms in the presence of low-quality data measurements. We further propose a data augmentation method to address the training data imbalance, which is caused by the rare occurrence of events. Moreover, we propose an adaptive training process to update the AOIFD method so that it can adapt to the time-varying operating conditions of power systems. The proposed AOIFD algorithm is practical in the sense that it is a fast-response method that requires no system modeling information and no global communications. Case studies with both synthetic and realistic PMU data are conducted to validate the effectiveness of the proposed method.Keywords
Funding Information
- General Research Funding (14200315)
- Research Grants Council of Hong Kong and the Shenzhen Institute of Artificial Intelligence and Robotics for Society
This publication has 22 references indexed in Scilit:
- Online Detection of Low-Quality Synchrophasor Measurements: A Data-Driven ApproachIEEE Transactions on Power Systems, 2016
- Power System Transient Stability Assessment Based on Big Data and the Core Vector MachineIEEE Transactions on Smart Grid, 2016
- Deep learningNature, 2015
- Synchrophasor time skew: Formulation, detection and correctionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Fault Detection, Identification, and Location in Smart Grid Based on Data-Driven Computational MethodsIEEE Transactions on Smart Grid, 2014
- Dimensionality Reduction of Synchrophasor Data for Early Event Detection: Linearized AnalysisIEEE Transactions on Power Systems, 2014
- Comprehensive Clustering of Disturbance Events Recorded by Phasor Measurement UnitsIEEE Transactions on Power Delivery, 2013
- Isolation-Based Anomaly DetectionACM Transactions on Knowledge Discovery From Data, 2012
- Outlier detection and robust covariance estimation using mathematical programmingAdvances in Data Analysis and Classification, 2010
- Learning from Imbalanced DataIEEE Transactions on Knowledge and Data Engineering, 2009