Islanding Detection for Inverter-Based Distributed Generation Using Unsupervised Anomaly Detection

Adeel Arif, Kashif Imran, Qiushi Cui, Yang Weng

Research output: Contribution to journalArticlepeer-review

1 Scopus citations

Abstract

Islanding detection with the rising grid supporting inverter-based distributed generation is becoming more critical protection due to its high droop gains and overall decreased system inertia leading to rapid changes in the electrical parameters. Traditional methods for islanding detection in this regard are susceptible to significant problems such as non-detection zone, false-positive detection, and inefficient mode of validation. Therefore, to attenuate these problems, this paper proposes a hybrid islanding detection technique based on unsupervised anomaly detection using autoencoders. This technique uses the rate of change of frequency as primary and phase angles of the voltage and current as secondary detection parameters, demonstrating improved performance, reliability, and robustness due to its shared advantage of both active frequency drift and autoencoder. Furthermore, a dialectic model of offline and online validation schemes is also proposed to ensure the reliability of detection. Extensive simulations and validations have been carried out on multiple networks to generate data sets used to train, test, and validate the technique and compute its statistical significance, thereby confirming its effectiveness. The optimal islanding detection time for the base cases was recorded as 20 milliseconds with an F1-score of 0.991, dependability index of 0.998, security index of 0.995, with total harmonic distortion of 4.56% and zero non-detection zones, which complies with IEC 61000-3-2 and IEEE standard 1547's requirement of detection within two seconds after islanding.

Original languageEnglish (US)
Article number9462826
Pages (from-to)90947-90963
Number of pages17
JournalIEEE Access
Volume9
DOIs
StatePublished - 2021

Keywords

  • Islanding
  • distributed power generation
  • microgrids
  • unsupervised learning

ASJC Scopus subject areas

  • Computer Science(all)
  • Materials Science(all)
  • Engineering(all)

Cite this