Abstract
Anomaly detection is of considerable significance in engineering applications, such as the monitoring and control of large-scale energy systems. This paper 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 <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ZCA</i> or <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ZCA-cor</i> whitening matrix with a small additional offset.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call