Improved Anomaly Detection and Localization Using Whitening-Enhanced Autoencoders

Journal Article (2024)
Author(s)

Chenguang Wang (TU Delft - Intelligent Electrical Power Grids)

Simon Tindemans (TU Delft - Intelligent Electrical Power Grids)

Peter Palensky (TU Delft - Intelligent Electrical Power Grids)

Research Group
Intelligent Electrical Power Grids
Copyright
© 2024 C. Wang, Simon H. Tindemans, P. Palensky
DOI related publication
https://doi.org/10.1109/TII.2023.3268685
More Info
expand_more
Publication Year
2024
Language
English
Copyright
© 2024 C. Wang, Simon H. Tindemans, P. Palensky
Research Group
Intelligent Electrical Power Grids
Issue number
1
Volume number
20
Pages (from-to)
659-668
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Anomaly detection is of considerable significance in engineering applications, such as the monitoring and control of large-scale energy systems. This article investigates the ability to accurately detect and localize the source of anomalies, using an autoencoder neural network-based detector. Correlations between residuals are identified as a source of misclassifications, and whitening transformations that decorrelate input features and/or residuals are analyzed as a potential solution. For two use cases, regarding spatially distributed wind power generation and temporal profiles of electricity consumption, the performance of various data processing combinations was quantified. Whitening of the input data was found to be most beneficial for accurate detection, with a slight benefit for the combined whitening of inputs and residuals. For localization of anomalies, whitening of residuals was preferred, and the best performance was obtained using standardization of the input data and whitening of the residuals using the zero-phase component analysis (ZCA) or zero-phase component analysis-correlation (ZCA-cor) whitening matrix with a small additional offset.

Files

Improved_Anomaly_Detection_and... (pdf)
(pdf | 3.75 Mb)
- Embargo expired in 03-01-2024
License info not available