Power systems today have to deal with more and more power quality issues (PQDs) like voltage drops, rises, harmonics, and transients because more people are using renewable energy sources and electronic devices. These problems can hurt equipment, stop services, and lower the overall reliability of power. In real-time settings, traditional detection methods often don't work as quickly or accurately as they should. This paper looks at how deep learning models, like Convolutional Neural Networks (CNNs), Long Short- Term Memory (LSTM) networks, and their hybrid (CNN-LSTM) versions, can accurately classify PQDs using data from electrical signals. We get very good at finding disturbances by training these models on changed signals using methods like wavelet and Fourier transforms. The results show that deep learning not only makes classification work better, but it also makes monitoring in smart grid systems faster and more reliable. The performance of the proposed models is evaluated using standard classification metrics, including accuracy, precision, recall, and F1-score. Experimental analysis demonstrates that the hybrid CNN-LSTM model provides superior classification performance by effectively combining the feature extraction capability of CNN with the sequence-learning ability of LSTM. The proposed framework achieves high classification accuracy, enhances disturbance recognition, and reduces the possibility of misclassification when compared with conventional machine learning approaches. Furthermore, the developed model supports faster decision-making, making it suitable for real-time monitoring and intelligent control applications in modern smart grids. The findings of this study indicate that advanced deep learning techniques offer a reliable and scalable solution for automated power quality disturbance classification, contributing to improved power system reliability, operational efficiency, and the development of next- generation intelligent electrical networks.

Keywords - PQDs, Power Quality, Classification of PQ ,CNN,LSTM, CNN+LSTM,PQDs, Power Quality Disturbances (PQDs), Deep Learning, CNN–LSTM, Smart Grid, MATLAB/Simulink, Electrical Signal Classification

🔒 This is a subscription article

Full text is available to subscribers and institutional members. Please choose an option below to access it.

1. Bollen MH. Understanding power quality problems. New York: IEEE press; 2000 Feb.
2. Navare DS, Kapde YR, Maurya S, Pardeshi DB, William P. Robotic Bomb Detection and Disposal: Application using Arduino. In2022 7th International Conference on Communication and Electronics Systems (ICCES) 2022 Jun 22 (pp. 479-483). IEEE.
3. Khale R, Sangale R, Agrawal SK, Pardeshi D. Design and Realization of a Multi-Level DC-AC Converter for High-Efficiency Power Conversion. In2025 3rd International Conference on Inventive Computing and Informatics (ICICI) 2025 Jun 4 (pp. 1535-1541). IEEE.
4. Kopare A, Shinde A, Agrawal S, Pardeshi DB. Efficient Power Converter Using Solar System. In2025 3rd International Conference on Inventive Computing and Informatics (ICICI) 2025 Jun 4 (pp. 1542-1547). IEEE.
5. Kopare A, Shinde A, Agrawal S, Pardeshi DB. Efficient Power Converter Using Solar System. In2025 3rd International Conference on Inventive Computing and Informatics (ICICI) 2025 Jun 4 (pp. 1542-1547). IEEE.
6. Stones J, Collinson A. Power quality. Power Engineer. 2001 Apr;15(2):58-64.
7. Mishra S, Bhende CN, Panigrahi BK. Detection and classification of power quality disturbances using S- transform and probabilistic neural network. IEEE Transactions on power delivery. 2008 Jan 31;23(1):280-7.
8. Caicedo JE, Agudelo-Martínez D, Rivas-Trujillo E, Meyer J. A systematic review of real-time detection and classification of power quality disturbances. Protection and Control of Modern Power Systems. 2023 Jan;8(1):1- 37.
9. LeCun Y, Bengio Y, Hinton G. Deep learning. nature. 2015 May 28;521(7553):436-44.
10. Goodfellow I, Bengio Y, Courville A, Bengio Y. Deep learning. Cambridge: MIT press; 2016 Nov 18.
11. Hochreiter S, Schmidhuber J. Long short-term memory. Neural computation. 1997 Nov 15;9(8):1735-80.
12. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. InProceedings of the IEEE conference on computer vision and pattern recognition 2016 (pp. 770-778).
13. Ashish V. Attention is all you need. Advances in neural information processing systems. 2017.
14. Choong F, Reaz MB, Mohd-Yasin F. Advances in signal processing and artificial intelligence technologies in the classification of power quality events: a survey. Electric Power Components and Systems. 2005 Dec 1;33(12):1333-49.
15. Huang CH, Lee CH, Shih KJ, Wang YJ. Frequency estimation of distorted power system signals using robust extended complex kalman filter. In2007 International Conference on Intelligent Systems Applications to Power Systems 2007 Nov 5 (pp. 1-6). IEEE.
16. Khokhar S, Zin AA, Memon AP, Mokhtar AS. A new optimal feature selection algorithm for classification of power quality disturbances using discrete wavelet transform and probabilistic neural network. Measurement. 2017 Jan 1;95:246-59.
17. Dash PK, Panigrahi BK, Sahoo DK, Panda G. Power quality disturbance data compression, detection, and classification using integrated spline wavelet and S-transform. IEEE Transactions on Power Delivery. 2003 Apr 30;18(2):595-600.
18. Mishra M. Power quality disturbance detection and classification using signal processing and soft computing techniques: A comprehensive review. International transactions on electrical energy systems. 2019 Aug;29(8):e12008.
19. Cai K, Cao W, Aarniovuori L, Pang H, Lin Y, Li G. Classification of power quality disturbances using Wigner- Ville distribution and deep convolutional neural networks. IEEe Access. 2019 Aug 23;7:119099-109.
20. Cen S, Kim DO, Lim CG. A fused CNN‐LSTM model using FFT with application to real‐time power quality disturbances recognition. Energy Science & Engineering. 2023 Jul;11(7):2267-80.
21. Hussain MR, Refaat SS, Abu-Rub H. Overview and partial discharge analysis of power transformers: A literature review. Ieee Access. 2021 Apr 23;9:64587-605.

Power systems today have to deal with more and more power quality issues (PQDs) like voltage drops, rises, harmonics, and transients because more people are using renewable energy sources and electronic devices. These problems can hurt equipment, stop services, and lower the overall reliability of power. In real-time settings, traditional detection methods often don't work as quickly or accurately as they should. This paper looks at how deep learning models, like Convolutional Neural Networks (CNNs), Long Short- Term Memory (LSTM) networks, and their hybrid (CNN-LSTM) versions, can accurately classify PQDs using data from electrical signals. We get very good at finding disturbances by training these models on changed signals using methods like wavelet and Fourier transforms. The results show that deep learning not only makes classification work better, but it also makes monitoring in smart grid systems faster and more reliable. The performance of the proposed models is evaluated using standard classification metrics, including accuracy, precision, recall, and F1-score. Experimental analysis demonstrates that the hybrid CNN-LSTM model provides superior classification performance by effectively combining the feature extraction capability of CNN with the sequence-learning ability of LSTM. The proposed framework achieves high classification accuracy, enhances disturbance recognition, and reduces the possibility of misclassification when compared with conventional machine learning approaches. Furthermore, the developed model supports faster decision-making, making it suitable for real-time monitoring and intelligent control applications in modern smart grids. The findings of this study indicate that advanced deep learning techniques offer a reliable and scalable solution for automated power quality disturbance classification, contributing to improved power system reliability, operational efficiency, and the development of next- generation intelligent electrical networks.

Keywords - PQDs, Power Quality, Classification of PQ ,CNN,LSTM, CNN+LSTM,PQDs, Power Quality Disturbances (PQDs), Deep Learning, CNN–LSTM, Smart Grid, MATLAB/Simulink, Electrical Signal Classification

🔒 This is a subscription article

Full text is available to subscribers and institutional members. Please choose an option below to access it.

1. Bollen MH. Understanding power quality problems. New York: IEEE press; 2000 Feb.
2. Navare DS, Kapde YR, Maurya S, Pardeshi DB, William P. Robotic Bomb Detection and Disposal: Application using Arduino. In2022 7th International Conference on Communication and Electronics Systems (ICCES) 2022 Jun 22 (pp. 479-483). IEEE.
3. Khale R, Sangale R, Agrawal SK, Pardeshi D. Design and Realization of a Multi-Level DC-AC Converter for High-Efficiency Power Conversion. In2025 3rd International Conference on Inventive Computing and Informatics (ICICI) 2025 Jun 4 (pp. 1535-1541). IEEE.
4. Kopare A, Shinde A, Agrawal S, Pardeshi DB. Efficient Power Converter Using Solar System. In2025 3rd International Conference on Inventive Computing and Informatics (ICICI) 2025 Jun 4 (pp. 1542-1547). IEEE.
5. Kopare A, Shinde A, Agrawal S, Pardeshi DB. Efficient Power Converter Using Solar System. In2025 3rd International Conference on Inventive Computing and Informatics (ICICI) 2025 Jun 4 (pp. 1542-1547). IEEE.
6. Stones J, Collinson A. Power quality. Power Engineer. 2001 Apr;15(2):58-64.
7. Mishra S, Bhende CN, Panigrahi BK. Detection and classification of power quality disturbances using S- transform and probabilistic neural network. IEEE Transactions on power delivery. 2008 Jan 31;23(1):280-7.
8. Caicedo JE, Agudelo-Martínez D, Rivas-Trujillo E, Meyer J. A systematic review of real-time detection and classification of power quality disturbances. Protection and Control of Modern Power Systems. 2023 Jan;8(1):1- 37.
9. LeCun Y, Bengio Y, Hinton G. Deep learning. nature. 2015 May 28;521(7553):436-44.
10. Goodfellow I, Bengio Y, Courville A, Bengio Y. Deep learning. Cambridge: MIT press; 2016 Nov 18.
11. Hochreiter S, Schmidhuber J. Long short-term memory. Neural computation. 1997 Nov 15;9(8):1735-80.
12. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. InProceedings of the IEEE conference on computer vision and pattern recognition 2016 (pp. 770-778).
13. Ashish V. Attention is all you need. Advances in neural information processing systems. 2017.
14. Choong F, Reaz MB, Mohd-Yasin F. Advances in signal processing and artificial intelligence technologies in the classification of power quality events: a survey. Electric Power Components and Systems. 2005 Dec 1;33(12):1333-49.
15. Huang CH, Lee CH, Shih KJ, Wang YJ. Frequency estimation of distorted power system signals using robust extended complex kalman filter. In2007 International Conference on Intelligent Systems Applications to Power Systems 2007 Nov 5 (pp. 1-6). IEEE.
16. Khokhar S, Zin AA, Memon AP, Mokhtar AS. A new optimal feature selection algorithm for classification of power quality disturbances using discrete wavelet transform and probabilistic neural network. Measurement. 2017 Jan 1;95:246-59.
17. Dash PK, Panigrahi BK, Sahoo DK, Panda G. Power quality disturbance data compression, detection, and classification using integrated spline wavelet and S-transform. IEEE Transactions on Power Delivery. 2003 Apr 30;18(2):595-600.
18. Mishra M. Power quality disturbance detection and classification using signal processing and soft computing techniques: A comprehensive review. International transactions on electrical energy systems. 2019 Aug;29(8):e12008.
19. Cai K, Cao W, Aarniovuori L, Pang H, Lin Y, Li G. Classification of power quality disturbances using Wigner- Ville distribution and deep convolutional neural networks. IEEe Access. 2019 Aug 23;7:119099-109.
20. Cen S, Kim DO, Lim CG. A fused CNN‐LSTM model using FFT with application to real‐time power quality disturbances recognition. Energy Science & Engineering. 2023 Jul;11(7):2267-80.
21. Hussain MR, Refaat SS, Abu-Rub H. Overview and partial discharge analysis of power transformers: A literature review. Ieee Access. 2021 Apr 23;9:64587-605.