Comparative Analysis of CNN and Hybrid CNN-LSTM Models for PQD Classification with Explainability Insights
Name
futureinternet-18-00514.pdf
Size
3.26 MB
Format
Adobe PDF
Checksum (MD5)
027179279c0c9157efe4b14065cf8e4d
Author(s)
Gurudas, Sreshtamol K
Satheesh, Rahul
Sreekumar, Sreenu
Alhelou, Hassan Haes
Date Issued
September 28, 2026
Journal
Future Internet
Publisher
Multidisciplinary Digital Publishing Institute
Citation
Gurudas, S.K.; Satheesh, R.; Sreekumar, S.; Alhelou, H.H. Comparative Analysis of CNN and Hybrid CNN-LSTM Models for PQD Classification with Explainability Insights. Future Internet 2026, 18, 514.
Version
Final published version
Abstract
Power Quality Disturbances (PQDs) must be accurately detected and classified to preserve stability, efficiency, and power reliability in modern power systems as nonlinear loads and renewable energy sources become more common. Despite the excellent classification accuracy of Deep Learning (DL) models, their computational complexity and implementation feasibility are often overlooked. This work uses time-frequency representations obtained from the Fourier Synchrosqueezing Transform (FSST) to assess several DL architectures for PQD classification. To assess performance and efficiency, the standalone Convolutional Neural Networks (CNNs) and CNN–recurrent models are analyzed. With DenseNet-based architectures achieving the best performance, the analyzed models exhibit high, closely spaced classification accuracies, typically ranging from 98% to 99.4%. The study underlines the importance of evaluating both computational performance and efficiency, which also shows that such slight accuracy gains often come at the expense of significantly greater computational complexity. In addition to classification accuracy, this study also highlights model explainability. Gradient-weighted Class Activation Mapping (Grad-CAM) is used to show discriminative regions in FSST representations, which sheds light on the DL models’ decision-making process.
MIT Department
Massachusetts Institute of Technology. School of Engineering
Terms of Use
Creative Commons Attribution
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.3390/fi18100514
