• Home
  • Search
  • Auto-Starting Semisupervised-Learning-Based Identification of Synchrophasor Data Anomalies
  • Cite Icon9
  • https://doi.org/10.1109/jiot.2022.3142103Copy DOI Icon

Auto-Starting Semisupervised-Learning-Based Identification of Synchrophasor Data Anomalies

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

In Internet of Things (IoT)-enabled modern power grids, advanced IoT devices, e.g., synchronous phasor measurement units (PMUs), have been widely deployed to closely monitor the grids’ states and dynamics. In practice, however, PMU measurements are often contaminated with anomalous (low-quality) data, e.g., data spikes, unchanged data, data losses/dropouts, and high-level data errors. To ensure the reliability of various PMU data-based applications, it is imperative to efficiently implement PMU data anomaly identification (PDAI). Focusing on performing online PDAI in a cost-effective way, this article develops an intelligent data-driven PDAI approach for practical power grids. Given the defect that the majority of the existing data-driven PDAI efforts necessitate costly domain expertise-based data annotation to start offline learning, the PDAI approach in this article is realized by designing an auto-starting semisupervised learning (SSL) scheme that automatically starts to learn from totally unlabeled PMU data. First, on the basis of the inherent spatial–temporal correlations in regional PMU measurements, sequential PMU data acquired from a specific power grid are characterized in a discriminative manner by profiling their spatial–temporal nearest neighbors (STNNs). With the exploration of the discriminability of STNN profiles, part of the obviously anomalous/normal data is reliably labeled on the basis of a statistical prior knowledge-based rule. Such an STNN-based preprocessing technique for partial data labeling enables the desirable auto-starting functionality of the whole SSL scheme. Then, taking both labeled and unlabeled data as inputs, a recurrent SSL machine for PDAI is efficiently built in two steps, i.e., unsupervised pretraining and supervised fine-tuning. Numerical test results with simulated PMU data from the Nordic test system and actual PMU data from two practical power grids illustrate the excellent PDAI performances of the proposed approach during the online application.

Similar Papers
  • Conference Article
  • Citations4

Investigating Machine Learning for Anomaly Detection in Phasor Measurement Unit Data

  • Apr 11, 2021
  • Connor Mcdonald +8
  • Research Article

A Novel Protective Logic for Optimal Coordination of Overcurrent Relays

  • Dec 01, 2015
  • Indonesian Journal of Electrical Engineering and Computer Science
  • Sajad Samadinasab +2
  • Conference Article
  • Citations2

Robustness to missing synchrophasor data for power and frequency event detection in electric grids

  • Nov 01, 2017
  • Sai Akhil R Konakalla +1
  • Research Article

A Novel Protective Logic for Optimal Coordination of Overcurrent Relays

  • Dec 01, 2015
  • TELKOMNIKA Indonesian Journal of Electrical Engineering
  • Sajad Samadinasab +2
  • Conference Article

Flawed Decompression of Swinging Door Algorithm in PMU Historians

  • Aug 01, 2018
  • Md Arif Khan +2
  • Conference Article
  • Citations27

Synthetic Dynamic PMU Data Generation: A Generative Adversarial Network Approach

  • May 01, 2019
  • Xiangtian Zheng +2
  • Conference Article
  • Citations10

Hybrid state estimation using distributed Compressive Sensing

  • Jul 01, 2016
  • Reza J Hamidi +3
  • Research Article
  • Citations60

An Alternating Direction Method of Multipliers Based Approach for PMU Data Recovery

  • Jul 01, 2019
  • IEEE Transactions on Smart Grid
  • Mang Liao +5
  • Research Article
  • Citations98

A Novel Event Detection Method Using PMU Data With High Precision

  • Jan 01, 2019
  • IEEE Transactions on Power Systems
  • Mingjian Cui +4
  • Conference Article
  • Citations3

Weakly Supervised Event Classification Using Imperfect Real-world PMU Data with Scarce Labels

  • Jul 17, 2022
  • Yunchuan Liu +1
  • Conference Article
  • Citations5

Application of Machine Learning for Online Dynamic Security Assessment in Presence of System Variability and Additive Instrumentation Errors

  • Oct 01, 2019
  • Anubhav Nath +2
  • Research Article
  • Citations14

Missing Value Replacement for PMU Data via Deep Learning Model With Magnitude Trend Decoupling

  • Jan 01, 2023
  • IEEE Access
  • Yuanbin Cheng +3
  • Research Article
  • Citations27

Anomaly detection in multivariate streaming PMU data using density estimation technique in wide area monitoring system

  • Mar 10, 2021
  • Expert Systems with Applications
  • A L Amutha +3
  • Research Article
  • Citations83

Statistical Characterization of PMU Error for Robust WAMS Based Analytics

  • Sep 12, 2019
  • IEEE Transactions on Power Systems
  • Tabia Ahmad +1
  • Research Article
  • Citations1

Deep Learning-Based Disturbance Detection in Smart Distribution Networks Using PMU Data

  • Jan 30, 2024
  • Journal of Electrical Engineering
  • Halim Kusuma
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.