Detection and Classification of Power Quality Disturbances with Feature Extraction and Machine Learning

Sıtkı Akkaya; Hasan Metehan Akgün; Emre Yüksek

doi:10.29137/ijerad.1460344

TR EN

Öznitelik Çıkarma ve Makine Öğrenimi ile Güç Kalitesi Bozunumlarının Tespiti ve Sınıflandırılması

Abstract

Güç kalitesi bozunumlarının (GKB) tespiti ve sınıflandırılması (TS), elektrik güç sistemlerinin güvenilirliğini, verimliliğini ve güvenliğini sağlamada önemli bir rol oynamaktadır. Zamanında tespit, ekipman hasarını ve arızalarını önleyerek koruyucu önlemlerin hızlı bir şekilde uygulanmasını sağlar. Ayrıca, sorun giderme ve planlı bakım sağlayarak arıza süresini azaltır ve sistem performansını optimize eder. Bu yüzden farklı gürültülü koşullar altında voltaj düşüşleri, yükselmeler, harmonikler, kesintiler gibi tekli-çoklu bozunumları içeren 21 sınıflı veriseti üretilmiştir. Üretilen veri setinden zaman serisi sinyalleri pencerelenmiş ve bu sinyallere, güç kalitesi bozunumlarının tespit ve sınıflandırılması için öznitelik çıkarımı işlemi uygulanmıştır. Çıkarılan özniteliklerin arasından da öznitelik seçim işlemi yapılmıştır. Seçilen öznitelikler giriş verisi olarak makine öğrenmesi algoritmalarına (MÖA) uygulanmıştır. Tespit ve sınıflandırma için yoğun öznitelik ve bu problemlere yönelik karşılaştımalı MÖA hiperparametre optimizasyonuna dayalı bir yaklaşım önerilmiştir. Karşılaştırmalı makine öğrenmesi algoritmalarından 10-çapraz doğrulama metriği ile elde edilen sonuçlara göre, en iyisi %96,97 ile Ekstrem Rassal Ağaçlar (ERA) olmak üzere sırasıyla Karar Ağaçları (KA), Çok Katmanlı Algılayıcı (ÇKA) ve Lojistik Regresyon’un (LR) %92,83, %83,31 ve %66,45 doğrulukla başarımlara sahip oldukları gösterilmiştir. Bu yaklaşım seçilen öznitelikler, optimize edilmiş hiperparametreler ve ilgili MÖA, tüm hiperparametre uzayında GKB'lerden sağlanan öznitelikler araştırılarak elde edildiğinden; yüksek doğruluk, düşük TS karmaşıklığı ile düşük hesaplama yükü avantajlarını beraberinde getirmektedir.

Keywords

Güç kalitesi bozunumları, Öznitelik çıkarımı, Sinyal işleme, Makine öğrenmesi, Tespit ve sınıflandırma

Supporting Institution

Sivas Bilim ve Teknoloji Üniversitesi

Thanks

Sivas Bilim ve Teknoloji Üniversitesi’ne çalışmada kullanılmak üzere sunmuş olduğu imkanlardan dolayı teşekkür ederiz.

Detection and Classification of Power Quality Disturbances with Feature Extraction and Machine Learning

Abstract

The detection and classification (D&C) of power quality disturbances (PQDs) are critical for ensuring the reliability, efficiency, and safety of modern electrical power systems. Prompt identification of these disturbances facilitates the swift implementation of protective measures, thereby preventing equipment damage and minimizing system downtime. This study presents a comprehensive framework for PQD D&C using an extensive 21-class dataset that incorporates both single and multiple disturbances, such as voltage sags, swells, harmonics, and interruptions, synthesized under a wide range of noise conditions (20–60 dB). The proposed methodology employs a dense feature space of 30 parameters,, including novel applications of periodograms and modified periodograms, extracted from windowed time-series signals. These features were utilized to train and optimize four machine learning algorithms within a rigorous hyperparameter search space. Based on 10-fold cross-validation, the Extra Trees (ET) algorithm achieved the superior performance with an accuracy of 96.97%, followed by Decision Trees (DT) at 92.83%, Multi-Layer Perceptron (MLP) at 83.31%, and Logistic Regression (LR) at 66.45%. The results demonstrate that the proposed ET-based approach offers high accuracy and robustness in noisy environments while maintaining a low computational load for real-time monitoring applications.

Keywords

Power quality disturbance, Feature extraction, Signal processing, Machine learning, Detection and classification, Extra Trees, Multi-Layer Perceptron, Decision Trees

References

Abdelsalam, A. A., Abdelaziz, A. Y., & Kamh, M. Z. (2021). A generalized approach for power quality disturbances recognition based on Kalman filter. IEEE Access, 9, 93614-93628, doi: 10.1109/ACCESS.2021.3093367.
Abdelsalam, A. A., Eldesouky, A. A., & Sallam, A. A. (2012). Classification of power system disturbances using linear Kalman filter and fuzzy-expert system. International Journal of Electrical Power & Energy Systems, 43(1), 688-695, doi: 10.1016/j.ijepes.2012.05.052.
Akkaya, S., & Salor Durna, Ö. (2019). Enhanced spectral decomposition method for light flicker evaluation of incandescent lamps caused by electric arc furnaces. Journal of the Faculty of Engineering and Architecture of Gazi University, 34(2), doi: 10.17341/gazimmfd.460497.
Akkaya, S., & Salor, Ö. (2018). A new flicker detection method for new generation lamps both robust to fundamental frequency deviation and based on the whole voltage frequency spectrum. Electronics, 7(6), 99, doi: 10.3390/electronics7060099.
Akkaya, S., & Salor, Ö. (2019). New flickermeter sensitive to high‐frequency interharmonics and robust to fundamental frequency deviations of the power system. IET Science, Measurement & Technology, 13(6), 783-793, doi: 10.1049/iet-smt.2018.5338.
Akkaya, S., & Salor, Ö. (2022). Flicker detection algorithm based on the whole voltage frequency spectrum for new generation lamps–Enhanced VPD Flickermeter model and Flicker curve. Electric Power Components and Systems, 49(6-7), 637-651, doi: 10.1080/15325008.2021.2011487.
Akkaya, S., Yüksek, E., & Akgün, H. M. (2024). A New Comparative Approach Based on Features of Subcomponents and Machine Learning Algorithms to Detect and Classify Power Quality Disturbances. Electric Power Components and Systems, 52(8), 1269-1292, doi: 10.1080/15325008.2023.2260375
Altay, T., & Baydoğan, M. G. (2021). A new feature-based time series classification method by using scale-space extrema. Engineering Science and Technology, an International Journal, 24(6), 1490-1497, doi: 10.1016/j.jestch.2021.03.017.
Chen, X., Li, K., & Xiao, J. (2018). Classification of power quality disturbances using dual strong tracking filters and rule‐based extreme learning machine. International Transactions on Electrical Energy Systems, 28(7), doi: 10.1002/etep.2560.
Crotti, G., D’Avanzo, G., Letizia, P. S., & Luiso, M. (2021). Measuring harmonics with inductive voltage transformers in presence of subharmonics. IEEE Transactions on Instrumentation and Measurement, 70, 1-13, doi: 10.1109/TIM.2021.3111995.

Hafiz, F., Swain, A., Naik, C., Abecrombie, S., & Eaton, A. (2019). Identification of power quality events: selection of optimum base wavelet and machine learning algorithm. IET Science, Measurement & Technology, 13(2), 260-271, doi: 10.1049/iet-smt.2018.5044.
IEC. (2008). IEC Standard 61000-4-7: General guide on harmonics and interharmonics measurements and measuring instruments for power supply networks and attached devices used for the measurements.
IEC. (2015). IEC Standard 61000-4-30: Testing and measurement techniques - Power quality measurement methods, vol. 2015, p. 90.
IEEE. (2010). Standard Definitions for the Measurement of Electric Power Quantities Under Sinusoidal, Nonsinusoidal, Balanced, or Unbalanced Conditions. IEEE Std 1459-2010 (Revision of IEEE Std 1459-2000), vol., no., pp.1-50, doi: 10.1109/IEEESTD.2010.5439063.
IEEE. (2011). Recommended Practice-Adoption of IEC 61000-4-15:2010, Electromagnetic compatibility (EMC)-Testing and measurement techniques-Flickermeter-Functional and design specifications. IEEE Std 1453-2011, vol., no., pp.1-58, doi: 10.1109/IEEESTD.2011.6053977.
IEEE. (2019). Recommended Practice for Monitoring Electric Power Quality. IEEE Std 1159-2019 (Revision of IEEE Std 1159-2009), vol., no., pp.1-98, doi: 10.1109/IEEESTD.2019.8796486.
Kapoor, R., Kumar, R., & Tripathi, M. M. (2018). Volterra bound interval type‐2 fuzzy logic‐based approach for multiple power quality events analysis. IET Electrical Systems in Transportation, 8(3), 188-196, doi: 10.1049/iet-est.2017.0054.
Karasu, S., & Saraç, Z. (2020). Classification of power quality disturbances by 2D-Riesz Transform, multi-objective grey wolf optimizer and machine learning methods. Digital signal processing, 101, 102711, doi: 10.1016/j.dsp.2020.102711.
Khetarpal, P., & Tripathi, M. M. (2020). A critical and comprehensive review on power quality disturbance detection and classification. Sustainable Computing: Informatics and Systems, 28, 100417, doi: 10.1016/j.suscom.2020.100417.
Kuwałek, P., & Wiczyński, G. (2021). Dependence of voltage fluctuation severity on clipped sinewave distortion of voltage. IEEE Transactions on Instrumentation and Measurement, 70, 1-8, doi: 10.1109/TIM.2021.3102693.
Liu, Y., Jin, T., Mohamed, M. A., & Wang, Q. (2021). A novel three-step classification approach based on time-dependent spectral features for complex power quality disturbances. IEEE Transactions on Instrumentation and Measurement, 70, 1-14, doi: 10.1109/TIM.2021.3050187.
Lv, J. (2022). Transient stability assessment in large-scale power systems using sparse logistic classifiers. International Journal of Electrical Power & Energy Systems, 136, 107626, doi: 10.1016/j.ijepes.2021.107626.
Manikandan, M. S., Samantaray, S. R., & Kamwa, I. (2014). Detection and classification of power quality disturbances using sparse signal decomposition on hybrid dictionaries. IEEE Transactions on Instrumentation and Measurement, 64(1), 27-38, doi: 10.1109/TIM.2014.2330493.
Manimala, K., Selvi, K., & Ahila, R. (2011). Hybrid soft computing techniques for feature selection and parameter optimization in power quality data mining. Applied Soft Computing, 11(8), 5485-5497, doi: 10.1016/j.asoc.2011.05.010.
Mishra, M. (2019). Power quality disturbance detection and classification using signal processing and soft computing techniques: A comprehensive review. International transactions on electrical energy systems, 29(8), doi: 10.1002/2050-7038.12008.
Narayanaswami, R., Sundaresan, D., & Prema, V. R. (2020). The mystery curve: a signal processing based power quality disturbance detection. IEEE Transactions on Industrial Electronics, 68(10), 10078-10086, doi: 10.1109/TIE.2020.3026268.
Reddy, M. J. B., Raghupathy, R. K., Venkatesh, K. P., & Mohanta, D. K. (2013). Power quality analysis using Discrete Orthogonal S-transform (DOST). Digital Signal Processing, 23(2), 616-626, doi: 10.1016/j.dsp.2012.09.013.
Sindi, H., Nour, M., Rawa, M., Öztürk, Ş., & Polat, K. (2021). A novel hybrid deep learning approach including combination of 1D power signals and 2D signal images for power quality disturbance classification. Expert Systems with Applications, 174, 114785, doi: 10.1016/j.eswa.2021.114785.
Singh, U., & Singh, S. N. (2017). Application of fractional Fourier transform for classification of power quality disturbances. IET Science, Measurement & Technology, 11(1), 67-76, doi: 10.1049/iet-smt.2016.0194.
Singh, U., & Singh, S. N. (2017). Detection and classification of power quality disturbances based on time–frequency‐scale transform. IET Science, Measurement & Technology, 11(6), 802-810, doi: 10.1049/iet-smt.2016.0395.
Tarjano Santos, C. H. & Pereira, V. (2022). Envelope estimation using geometric properties of a discrete real signal. Digital Signal Processing: A Review Journal, vol. 120, p. 103229, doi: 10.1016/j.dsp.2021.103229.
Tiwari, V. K., Umarikar, A. C., & Jain, T. (2020). Measurement of instantaneous power quality parameters using UWPT and Hilbert transform and its FPGA implementation. IEEE Transactions on Instrumentation and Measurement, 70, 1-13, doi: 10.1109/TIM.2020.3021769.
Turanoglu-Bekar, E., Ulutagay, G., & Kantarcı-Savas, S. (2016). Classification of thyroid disease by using data mining models: a comparison of decision tree algorithms. Oxford Journal of Intelligent Decision and Data Sciences, 2, 13-28, doi: 10.5899/2016/ojids-00002.
Uddin, S., Khan, A., Hossain, M. E., & Moni, M. A. (2019). Comparing different supervised machine learning algorithms for disease prediction. BMC medical informatics and decision making, 19(1), 1-16, doi: 10.1186/s12911-019-1004-8.
Verma, A. K., Jarial, R. K., Roncero-Sanchez, P., & Ungarala, M. R. (2021). Improved Fundamental Frequency Estimator for Three-Phase Application. IEEE Transactions on Industrial Electronics, vol. 68, no. 9, pp. 8992–8998, 2021, doi: 10.1109/TIE.2020.3018063.
Xi, Y., Li, Z., Zeng, X., Tang, X., Liu, Q., & Xiao, H. (2018). Detection of power quality disturbances using an adaptive process noise covariance Kalman filter. Digital Signal Processing, 76, 34-49, doi: 10.1016/j.dsp.2018.01.013.
Xiao, F., Lu, T., Wu, M., & Ai, Q. (2020). Maximal overlap discrete wavelet transform and deep learning for robust denoising and detection of power quality disturbance. IET Generation, Transmission & Distribution, 14(1), 140-147, doi: 10.1049/iet-gtd.2019.1121.
Yu, Y., Zhao, W., Li, S., & Huang, S. (2021). A two-stage wavelet decomposition method for instantaneous power quality indices estimation considering interharmonics and transient disturbances. IEEE Transactions on Instrumentation and Measurement, 70, 1-13, doi: 10.1109/TIM.2021.3052554.
Zaro, F. R. (2021). Power quality disturbances detection and classification rule-based decision tree. International Journal of Engineering Science and Application, 5(1), 1-6, doi: 10.37394/232014.2021.17.3.
Zu, X., & Wei, K. (2021). A simple gated recurrent network for detection of power quality disturbances. IET Generation, Transmission & Distribution, 15(4), 751-761, doi: 10.1049/gtd2.12056.

Details

Primary Language

English

Subjects

Decision Support and Group Support Systems, Electrical Energy Transmission, Networks and Systems, Evaluation Technique in Electronics

Journal Section

Research Article

Authors

Sıtkı Akkaya ^*
0000-0002-3257-7838
Türkiye

Hasan Metehan Akgün
0000-0002-8439-8946
Türkiye

Emre Yüksek
0000-0002-1885-5539
Türkiye

Publication Date

May 31, 2026

Submission Date

March 28, 2024

Acceptance Date

March 21, 2026

Published in Issue

Year 2026 Volume: 18 Number: 3

DOI

https://doi.org/10.29137/ijerad.1460344

IZ

https://izlik.org/JA87JN97EB

APA

Akkaya, S., Akgün, H. M., & Yüksek, E. (2026). Detection and Classification of Power Quality Disturbances with Feature Extraction and Machine Learning. International Journal of Engineering Research and Development, 18(3), 1-15. https://doi.org/10.29137/ijerad.1460344

AMA

1.Akkaya S, Akgün HM, Yüksek E. Detection and Classification of Power Quality Disturbances with Feature Extraction and Machine Learning. IJERAD. 2026;18(3):1-15. doi:10.29137/ijerad.1460344

Chicago

Akkaya, Sıtkı, Hasan Metehan Akgün, and Emre Yüksek. 2026. “Detection and Classification of Power Quality Disturbances With Feature Extraction and Machine Learning”. International Journal of Engineering Research and Development 18 (3): 1-15. https://doi.org/10.29137/ijerad.1460344.

EndNote

Akkaya S, Akgün HM, Yüksek E (May 1, 2026) Detection and Classification of Power Quality Disturbances with Feature Extraction and Machine Learning. International Journal of Engineering Research and Development 18 3 1–15.

IEEE

[1]S. Akkaya, H. M. Akgün, and E. Yüksek, “Detection and Classification of Power Quality Disturbances with Feature Extraction and Machine Learning”, IJERAD, vol. 18, no. 3, pp. 1–15, May 2026, doi: 10.29137/ijerad.1460344.

ISNAD

Akkaya, Sıtkı - Akgün, Hasan Metehan - Yüksek, Emre. “Detection and Classification of Power Quality Disturbances With Feature Extraction and Machine Learning”. International Journal of Engineering Research and Development 18/3 (May 1, 2026): 1-15. https://doi.org/10.29137/ijerad.1460344.

JAMA

1.Akkaya S, Akgün HM, Yüksek E. Detection and Classification of Power Quality Disturbances with Feature Extraction and Machine Learning. IJERAD. 2026;18:1–15.

MLA

Akkaya, Sıtkı, et al. “Detection and Classification of Power Quality Disturbances With Feature Extraction and Machine Learning”. International Journal of Engineering Research and Development, vol. 18, no. 3, May 2026, pp. 1-15, doi:10.29137/ijerad.1460344.

Vancouver

1.Sıtkı Akkaya, Hasan Metehan Akgün, Emre Yüksek. Detection and Classification of Power Quality Disturbances with Feature Extraction and Machine Learning. IJERAD. 2026 May 1;18(3):1-15. doi:10.29137/ijerad.1460344

Kırıkkale University, Faculty of Engineering and Natural Science, 71450 Yahşihan / Kırıkkale, Türkiye.

ijerad@kku.edu.tr

Öznitelik Çıkarma ve Makine Öğrenimi ile Güç Kalitesi Bozunumlarının Tespiti ve Sınıflandırılması

Abstract

Keywords

Supporting Institution

Thanks

Detection and Classification of Power Quality Disturbances with Feature Extraction and Machine Learning

Abstract

Keywords

References

Details

Primary Language

Subjects

Journal Section

Authors

Publication Date

Submission Date

Acceptance Date

Published in Issue

DOI

IZ

Cite