Classification of power quality failures by deep ensemble model

Vishakha Saurabh Shah, M.S. Ali and Saurabh A. Shah

International Journal of Industrial and Systems Engineering, 2026, vol. 53, issue 4, 425-450

Abstract: This developed method includes three major sections: 1) data normalisation; 2) feature extraction; 3) classification. In the initial phase, the collected PQ data is normalised in the data normalisation step. Then, the normalised data is given as input to the feature extraction. The time series features like rate of change (ROC), relative strength index (RSI), simple moving average (SMA) and standard deviation features were extracted. Then, the extracted features are trained by the ensemble classifier consisting of convolutional neural network (CNN) and cascaded neural network (Cas NN). The classifiers CNN and Cas NN run independently and concurrently with extracted features. The final output is taken by averaging the output of both classifiers. Finally, a comparative evaluation is undergone to validate the performance of the projected model with traditional classifiers and feature analysis.

Keywords: smart meters; utilities; power quality; data normalisation; renewable energy. (search for similar items in EconPapers)
Date: 2026
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.inderscience.com/link.php?id=155614 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ids:ijisen:v:53:y:2026:i:4:p:425-450

Access Statistics for this article

More articles in International Journal of Industrial and Systems Engineering from Inderscience Enterprises Ltd
Bibliographic data for series maintained by Sarah Parker ().