Wavelet-Assisted CNN-LSTM Classification of Power Quality Disturbances in Smart Grid Systems

Power quality disturbances are becoming more frequent as smart grids incorporate larger shares of renewable generation, distributed resources, power-electronic interfaces, and nonlinear loads. Because these events may be transient, non-stationary, or composed of several overlapping signatures, their automatic recognition remains difficult under realistic measurement noise. This study evaluates a classification framework in which a three-level Discrete Wavelet Transform (DWT) first provides a multi-resolution representation of each waveform, after which a one-dimensional Convolutional Neural Network (CNN) extracts local patterns and a Long Short-Term Memory (LSTM) layer models their temporal evolution. The experiments use 10,000 synthetic signals representing ten power-quality classes, including seven individual events and three combined disturbances. All samples were generated with parameters based on IEEE 1159-2019 and contaminated with additive white Gaussian noise at 30 dB SNR. On the 1,500-sample hold-out set, the model achieved an overall accuracy of 92.33%. Normal operation, voltage swell, harmonics, transient, interruption, and flicker were recognized without errors, whereas most residual confusion occurred between voltage sag and sag-plus-transient events. The measured CPU inference time was approximately 12 ms per sample. These findings show that wavelet-supported spatial-temporal learning can provide a practical basis for automated power-quality monitoring, while further validation on measured grid data is still required.

Power-quality disturbance classification; smart grids; discrete wavelet transform

1. M. H. J. Bollen and I. Y. H. Gu, Signal Processing of Power Quality Disturbances. Hoboken, NJ, USA: Wiley-IEEE Press, 2020. [Google Scholar] [Crossref]

2. IEEE Recommended Practice for Monitoring Electric Power Quality, IEEE Std 1159-2019 (Revision of IEEE Std 1159-2009), pp. 1-113, 2019. [Google Scholar] [Crossref]

3. S. Khokhar, et al., "A review on intelligent detection and classification of power quality disturbances using maximal overlap discrete wavelet transform and deep learning," IET Generation, Transmission & Distribution, vol. 17, no. 4, pp. 890-905, 2023. [Google Scholar] [Crossref]

4. I. Topaloglu, "Deep learning based a new approach for power quality disturbance classification," Journal of Electrical Engineering & Technology, vol. 18, no. 2, pp. 1125-1138, 2023. [Google Scholar] [Crossref]

5. A. K. Singh, et al., "Review of signal processing techniques and machine learning algorithms for power quality analysis in smart grids," Renewable and Sustainable Energy Reviews, vol. 168, p. 112845, 2022. [Google Scholar] [Crossref]

6. N. Wang, et al., "Identification of power quality disturbance characteristic based on deep learning," Electric Power Systems Research, vol. 226, p. 110015, 2024. [Google Scholar] [Crossref]

7. I. S. Samanta, et al., "A comprehensive review of deep-learning applications to power quality analysis in smart grid and microgrid scenarios," Energies, vol. 16, no. 11, p. 4406, 2023. [Google Scholar] [Crossref]

8. R. J. J. Molu, et al., "Enhancing power quality monitoring with discrete wavelet transform and deep learning in smart grid technologies," Frontiers in Energy Research, vol. 12, p. 1435704, 2024. [Google Scholar] [Crossref]

9. D. Li, et al., "A new deep learning method for classification of power quality disturbances," Computers & Electrical Engineering, vol. 115, p. 109123, 2024. [Google Scholar] [Crossref]

10. U. Güvencir, et al., "Online fine-grained root cause classification for power quality disturbances using hybrid deep learning," IEEE Access, vol. 12, pp. 11270-11285, 2024. [Google Scholar] [Crossref]

11. F. A. Albalooshi, et al., "Deep learning algorithm for automatic classification of power quality disturbances using hybrid CNN-LSTM," Applied Sciences, vol. 14, no. 3, p. 1442, 2024. [Google Scholar] [Crossref]

12. B. Patnaik, et al., "MODWT-XGBoost based smart energy solution for fault detection and power quality improvement in smart grids," Applied Energy, vol. 285, p. 116456, 2021. [Google Scholar] [Crossref]

13. Z. L. Gaing, "Wavelet-based neural network for power disturbance recognition and classification," IEEE Transactions on Power Delivery, vol. 19, no. 4, pp. 1560-1568, 2004. [Google Scholar] [Crossref]

14. R. Debnath, et al., "A hybrid AI framework for identification of power quality disturbances in complex grid environments," Scientific Reports, vol. 14, p. 35376, 2024. [Google Scholar] [Crossref]

15. J. De La Cruz, et al., "Review on interpretable machine learning in smart grid for power quality and fault location," Energies, vol. 16, no. 6, p. 2280, 2023. [Google Scholar] [Crossref]

16. Y. Kim and C. G. Lim, "A fused CNN-LSTM model using FFT and wavelet transform for efficient classification of power quality disturbances," International Journal of Engineering and Technology Innovation, vol. 13, no. 2, pp. 112-125, 2023. [Google Scholar] [Crossref]

17. R. Chinthaginjala, et al., "Hybrid AI and semiconductor approaches for power quality disturbance detection in hybrid power systems," Electrical Engineering, vol. 106, no. 3, pp. 3753-3768, 2024. [Google Scholar] [Crossref]

18. T. Das, et al., "Artificial intelligence based grid connected inverters for power quality improvement in smart grid applications: A review," IEEE Transactions on Smart Grid, vol. 14, no. 2, pp. 1120-1135, 2023. [Google Scholar] [Crossref]

19. M. A. Hossain, et al., "Hybrid deep networks for early detection of power quality disturbances in grid-connected distributed generation systems," IEEE Transactions on Power Delivery, vol. 38, no. 4, pp. 2890-2901, 2023. [Google Scholar] [Crossref]

20. P. K. Ray, et al., "A CNN-LSTM framework for power quality disturbance classification with enhanced noise robustness," IEEE Systems Journal, vol. 17, no. 3, pp. 4512-4523, 2023. [Google Scholar] [Crossref]

21. L. Zhang, et al., "An LSTM-based framework for predictive power quality assessment using kernel entropy component analysis and hybrid networks," IEEE Transactions on Instrumentation and Measurement, vol. 72, pp. 1-12, 2023. [Google Scholar] [Crossref]

22. S. Mishra, et al., "Detection and classification of power quality disturbances using segmented and modified S-transform and DCNN-MSVM hybrid," IEEE Transactions on Power Delivery, vol. 37, no. 5, pp. 4012-4021, 2022. [Google Scholar] [Crossref]

23. F. J. Perez, "A hybrid algorithm for recognition of power quality disturbances using wavelet packet transform and random forest," IEEE Access, vol. 8, pp. 229184-229200, 2020. [Google Scholar] [Crossref]

24. H. E. A. M. Yeh, "A hybrid approach for detection and classification of power quality disturbances using deep feature extraction," in Proc. IEEE Power & Energy Society General Meeting, pp. 1-5, 2022. [Google Scholar] [Crossref]

25. A. M. Shaikh, et al., "A comparative analysis of deep learning models for power quality disturbance classification," IEEE Access, vol. 11, pp. 72345-72358, 2023. [Google Scholar] [Crossref]

• What the Desert Fathers Teach Data Scientists: Ancient Ascetic Principles for Ethical Machine-Learning Practice
• Comparative Analysis of Some Machine Learning Algorithms for the Classification of Ransomware
• Comparative Performance Analysis of Some Priority Queue Variants in Dijkstra’s Algorithm
• Transfer Learning in Detecting E-Assessment Malpractice from a Proctored Video Recordings.
• Dual-Modal Detection of Parkinson’s Disease: A Clinical Framework and Deep Learning Approach Using NeuroParkNet