Power Quality Disturbance Classification Using Wavelet-Transform Features and Ensemble Machine Learning
DOI:
https://doi.org/10.38035/jgit.v4i1.784Keywords:
Power Quality, Wavelet Transform, Ensemble Learning, Catboost, Disturbance ClassificationAbstract
PQ disturbances, voltage sags, swells, interruptions, harmonics, flicker, and transients, degrade grid reliability and damage sensitive equipment. Automating their classification is essential for modern distribution-network monitoring, particularly in Indonesia's PLN grid, where renewable-energy integration accelerates PQ degradation. This study proposes a two-stage pipeline: DWT feature extraction followed by ensemble machine learning. Level-5 wavelet multiresolution analysis decomposes each voltage waveform using three wavelet families (db4, sym4, coif4), yielding 24 features per signal (energy, entropy, RMS, and standard deviation across six bands). Four classifiers, SVM (baseline), Random Forest, XGBoost, and CatBoost, are evaluated on 3,550 synthetic signals from IEEE 1159 parameters across 13 disturbance classes with realistic imbalance. SMOTE oversampling is applied to training folds only to prevent leakage. The best configuration (coif4 + CatBoost) achieves 94.2% accuracy and 0.932 macro-F1. On the public Mendeley PQ Dataset (699 samples, 12 classes), ensembles exceed 98% accuracy. A signal-to-noise-ratio sweep (20-50 dB) confirms graceful degradation: accuracy remains above 73% at 20 dB. Wavelet-domain features paired with gradient-boosted ensembles offer a reproducible, high-performance approach to PQ disturbance classification. The headless Python pipeline is lightweight and edge-deployable for IoT-ready smart-grid PQ monitoring.
References
Akkaya, S., & Dümen, S. (2025). A novel vision transformer-based power quality disturbance classification method. Ain Shams Engineering Journal, 16(11), 103718. https://doi.org/10.1016/j.asej.2025.103718
Bansal, M., Gupta, R., Singh, S., Kumar, R., Upadhyay, R., & Das, D. B. (2026). Trajectory circle-based composite power quality disturbance classification using synchro squeezed wavelet transform and vision transformer. Electric Power Systems Research, 252, 112460. https://doi.org/10.1016/j.epsr.2025.112460
Chamchuen, S., Siritaratiwat, A., Fuangfoo, P., Suthisopapan, P., & Khunkitti, P. (2021). Adaptive salp swarm algorithm as optimal feature selection for power quality disturbance classification. Applied Sciences, 11(12), 5670. https://doi.org/10.3390/app11125670
Chen, S., Li, Z., Pan, G., & Xu, F. (2022). Power quality disturbance recognition using empirical wavelet transform and feature selection. Electronics, 11(2), 174. https://doi.org/10.3390/electronics11020174
Choe, S., & Yoo, J. (2021). Wavelet packet transform modulus-based feature detection of stochastic power quality disturbance signals. Applied Sciences, 11(6), 2825. https://doi.org/10.3390/app11062825
Dzikrurrokhim, M. R., & Ahlgren, E. O. (2026). Target-based energy transitions in the electricity systems of Southeast Asia: A comparative study of Indonesia, the Philippines, and Vietnam. Renewable and Sustainable Energy Transition, 10, 100152. https://doi.org/10.1016/j.rset.2026.100152
Gong, F., Diao, R., Cai, C., & Han, J. (2026). POA-optimized 1D-CNN with channel attention for power quality disturbance classification under strong noise conditions. Energies, 19(15), 3514. https://doi.org/10.3390/en19153514
Greenwell, B. M. (2022). Gradient boosting machines. In Tree-based methods for statistical learning in R. Chapman and Hall/CRC. https://doi.org/10.1201/9781003089032-8
Harriz, M. A., Akbariani, N. V., Setiyowati, H., & Santoso, H. (2023). Enhancing the efficiency of Jakarta's mass rapid transit system with XGBoost algorithm for passenger prediction. Jambura Journal of Informatics, 5(1), 1-6. https://doi.org/10.37905/jji.v5i1.18814
Harriz, M. A., & Setiyowati, H. (2023). Komparasi algoritma decision tree dan KNN dalam mengklasifikasikan daerah berdasarkan produksi listrik. JIKO (Jurnal Informatika dan Komputer), 7(2), 167. https://doi.org/10.26798/jiko.v7i2.787
Harriz, M. A., Setiyowati, H., & Akbariani, N. V. (2025). A literature review on IoT applications in fishery cold chains: Integrating blue economy principles for sustainable food security. Journal of Food Technology Research, 12(4), 380-393. https://doi.org/10.18488/jftr.v12i4.4631
IEEE. (2019). IEEE recommended practice for monitoring electric power quality (IEEE Std 1159-2019). https://doi.org/10.1109/IEEESTD.2019.8796486
Ismael, M. R., Abd, H. J., & Homod, R. Z. (2024). An algorithm for the classification of power quality disturbance signals using a tunable-Q-factor wavelet transform and ensemble learning methodology. Electrical Engineering, 106, 5253-5265. https://doi.org/10.1007/s00202-024-02294-y
Janthong, S., & Phukpattaranont, P. (2025). Power quality disturbance detection using improved grasshopper optimization and adaptive boosted random forest. Electrical Engineering, 107, 14265-14300. https://doi.org/10.1007/s00202-025-03260-y
Juarez, M., Zamora, A., Ortiz-Bejar, J., Silva, J., Cerda, J., & Paternina, M. (2024). PQ-SyDa: Power quality synthetic disturbances dataset. In Proceedings of the IEEE PES Generation, Transmission and Distribution Latin America Conference and Industrial Exposition (GTDLA) (pp. 1-6). IEEE. https://doi.org/10.1109/gtdla61236.2024.10913752
Kee, O. K. H., Kee, K.-K., Yong, C. Y., Rashidi, R., & Lo, T. H. (2025). Development of a data-driven energy monitoring system for power consumption and power quality monitoring. Journal of Renewable Energy and Smart Grid Technology, 20, 163-175. https://doi.org/10.69650/rast.2025.263660
Khaldi, B., Dekhandji, F., & Recioui, A. (2025). Low-cost IoT-based smart meter for real-time power quality monitoring and disturbance detection using embedded 1D CNN. Journal of Energy Systems, 9(4), 365-379. https://doi.org/10.30521/jes.1718242
Korstanje, J. (2025). Gradient boosting with XGBoost, LightGBM, and CatBoost. In Advanced forecasting with Python. Apress. https://doi.org/10.1007/979-8-8688-2028-1_16
Li, S., Zhu, X., & Zhou, D. (2025). Power quality disturbance signal denoising and detection based on improved DBO-VMD combined with wavelet thresholding. Electric Power Systems Research*, 238, 111193. https://doi.org/10.1016/j.epsr.2024.111193
Liu, J. (2021). Importance-SMOTE: A synthetic minority oversampling method for noisy imbalanced data. Soft Computing, 26(3), 1141-1163. https://doi.org/10.1007/s00500-021-06532-4
Madgula, S., Veeramsetty, V., & Durgam, R. (2025). Signal processing approaches for power quality disturbance classification: A comprehensive review. Results in Engineering, 25, 104569. https://doi.org/10.1016/j.rineng.2025.104569
Mahla, R., & Garg, M. M. (2024). Power quality disturbances and detection methods: A brief review. In Proceedings of the IEEE 11th Power India International Conference (PIICON) (pp. 1-6). IEEE. https://doi.org/10.1109/piicon63519.2024.10995132
Mishra, M. K. (2023). Power quality in power distribution systems: Concepts and applications. CRC Press. https://doi.org/10.1201/9781032617305
Palomares-Salas, J. C., Aguado-González, S., & Sierra-Fernández, J. M. (2025). Robustness of machine learning and deep learning models for power quality disturbance classification: A cross-platform analysis. Applied Sciences, 15(19), 10602. https://doi.org/10.3390/app151910602
Reyseliani, N., Hidayatno, A., & Purwanto, W. W. (2022). Implication of the Paris agreement target on Indonesia electricity sector transition to 2050 using TIMES model. Energy Policy, 169, 113184. https://doi.org/10.1016/j.enpol.2022.113184
Shiroya, N. J., Dey, M., & Rana, S. P. (2026). Ensemble learning for event detection and disturbance classification in power quality data from solar energy systems. Next Energy, 11, 100556. https://doi.org/10.1016/j.nxener.2026.100556
Uzel, H. (2025). An explainable hybrid deep learning approach for power quality disturbance classification. Bulletin of the Polish Academy of Sciences: Technical Sciences, Article 157326. https://doi.org/10.24425/bpasts.2026.157326
Veeramsetty, V., Gundapu, R. K., Aitha, D., & Aluri, N. (2023). PQ disturbances dataset [Data set]. Mendeley Data. https://doi.org/10.17632/nkdpg8mn4f.3
Wang, J., & Awang, N. (2026). SVED-SMOTE: Support vector enhanced density SMOTE oversampling technique for imbalanced data classification. International Journal of Machine Learning and Cybernetics, 17. https://doi.org/10.1007/s13042-026-03240-z
Wang, T., Zhuo, J., Hou, Y., Lu, Z., & Li, Y. (2026). Power quality disturbance classification via a time-frequency feature-fused transformer model with cross-attention mechanism. Electric Power Systems Research, 251, 112330. https://doi.org/10.1016/j.epsr.2025.112330
Xu, W., Wang, R., Zhang, Y., Wang, J., Wang, Z., Wu, X., Li, W., Li, X., Zhang, M., & Sun, L. (2026). A power quality disturbance classification method using a hybrid transformer and discrete wavelet transform model. Electric Power Systems Research, 253, 112547. https://doi.org/10.1016/j.epsr.2025.112547
Yang, S., Shan, T., & Yang, X. (2025). Interpretable DWT-1DCNN-LSTM network for power quality disturbance classification. Energies, 18(2), 231. https://doi.org/10.3390/en18020231
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Muhammad Alfathan Harriz
This work is licensed under a Creative Commons Attribution 4.0 International License.
Hak cipta :
Penulis yang mempublikasikan manuskripnya di jurnal ini menyetujui ketentuan berikut:
- Hak cipta pada setiap artikel adalah milik penulis.
- Penulis mengakui bahwa Jurnal Greenation Ilmu Teknik (JGIT) berhak menjadi yang pertama menerbitkan dengan lisensi Creative Commons Attribution 4.0 International (Attribution 4.0 International CC BY 4.0) .
- Penulis dapat mengirimkan artikel secara terpisah, mengatur distribusi non-eksklusif manuskrip yang telah diterbitkan dalam jurnal ini ke versi lain (misalnya, dikirim ke repositori institusi penulis, publikasi ke dalam buku, dll.), dengan mengakui bahwa manuskrip telah diterbitkan pertama kali di JGIT.
