A Deep Learning Approach to Power Quality Monitoring for Energy Efficiency and Carbon Reduction

Kevser İrem Danaci; Sıtkı Akkaya

doi:10.65582/gd.2026.007

Authors

Kevser İrem Danaci Department of Electrical Electronics Eng., Sivas University of Science and Technology, Sivas, Turkey. https://orcid.org/0000-0002-4654-5140
Sıtkı Akkaya Department of Electrical Electronics Eng., Sivas University of Science and Technology, Sivas, Turkey. https://orcid.org/0000-0002-3257-7838

DOI:

https://doi.org/10.65582/gd.2026.007

Keywords:

Power Quality Disturbance Detection, Deep Learning, Carbon Emissions, AI for Energy Efficiency, Signal Processing in Power Systems, Smart Grid, Neural Networks

Abstract

A classification system using deep learning for detecting power quality disturbances (PQDs), which are commonly experienced in electric power systems, has been proposed in this study. Because reliable and efficient classification methods are becoming increasingly critical as new forms of energy are integrated into the electric grid and as smart grid technology advances, accurate detection of PQDs will significantly contribute to the stability, efficiency, and robustness of current electric power systems. The SEED power quality disturbance dataset has been used for analysis; it contains 17 different types of disturbances, including pure sinusoidal signals. Both the raw 1D time domain signals and the 2D time frequency representations have been used to train the models (the time-frequency representations were created with the Short Term Fourier Transform, or STFT). The models used were convolutional neural network (CNN) architectures adapted for both 1D and 2D input data; both types of architectures were compared using accuracy, precision, and recall as measures of performance. The experimental results of the study show that for test accuracy, the 1D CNN model performed better than the 2D CNN model (i.e., 95% versus 82%, respectively). This research differs from most previous work because it simultaneously examines a common set of time domain and time-frequency feature representations while keeping all other test conditions constant. Results suggest that temporal representations of raw PQ signals may provide a classification advantage over time-frequency representations when used for PQD classification. Such benefits associated with using temporal representations will aid in the design of effective and accurate PQ monitoring systems, which, together with improved efficiencies from energy conservation, can help contribute towards global carbon emission reduction objectives by both reducing and eliminating wasted energy based on accurate and timely detection of power quality problems using intelligent monitoring techniques in modern smart grids.

References

Albalooshi, F. A. and Qader, M. R., 2025. Deep Learning Algorithm for Automatic Classification of Power Quality Disturbances, Applied Sciences (Switzerland). Multidisciplinary Digital Publishing Institute, 15(3), p. 1442. DOI: doi.org/10.3390/APP15031442.

Bai, H. et al., 2025. Power Quality Disturbance Classification Strategy Based on Fast S-Transform and an Improved CNN-LSTM Hybrid Model, Processes, 13(3), pp. 1–20. DOI: doi.org/10.3390/pr13030743.

Baig, M. A. A. et al., 2024. An Ensemble Deep CNN Approach for Power Quality Disturbance Classification: A Technological Route Towards Smart Cities Using Image-Based Transfer, Future Internet, 16(12), pp. 1–24. DOI: doi.org/10.3390/fi16120436.

Bollen, M. H. J., 2003. What is power quality?, Electric Power Systems Research, 66(1), pp. 5–14. DOI: doi.org/10.1016/S0378-7796(03)00067-1.

Cai, J., Zhang, K. and Jiang, H., 2023. Power Quality Disturbance Classification Based on Parallel Fusion of CNN and GRU, Energies, 16(10). DOI: doi.org/10.3390/en16104029.

Caicedo, J. E. et al., 2023, A systematic review of real-time detection and classification of power quality disturbances, Protection and Control of Modern Power Systems. Springer Nature Singapore, 8(1). DOI: doi.org/10.1186/s41601-023-00277-y.

Channa, I. A. and Li, D., 2023. Detection and classification of power quality disturbances using STFT and deep neural Network, ACM International Conference Proceeding Series, pp. 461–466. DOI: doi.org/10.1145/3638584.3638596.

Chiam, D. H., Lim, K. H. and Law, K. H., 2023. LSTM power quality disturbance classification with wavelets and attention mechanism, Electrical Engineering. Springer Berlin Heidelberg, 105(1), pp. 259–266. DOI: doi.org/10.1007/s00202-022-01667-5.

Ding, Y. et al., 2025. Carbon management for modern power system: An overview, Smart Power & Energy Security. The Authors, 1(1), pp. 12–24. DOI: doi.org/10.1016/j.spes.2024.06.001.

Electricity Maps ApS, 2025. Electricity Maps. Available at: https://app.electricitymaps.com/map/72h/hourly (Accessed: 21 August 2025).

Garcia, C. I. et al., 2020. A Comparison of Power Quality Disturbance Detection and Classification Methods Using CNN, LSTM and CNN-LSTM, Applied Sciences. Multidisciplinary Digital Publishing Institute, 10(19), p. 6755. DOI: doi.org/10.3390/APP10196755.

IEEE SA - IEEE 1159-2019, 2019. Available at: https://standards.ieee.org/ieee/1159/6124/ (Accessed: 15 August 2025).

Igual, R. et al., 2018. Integral mathematical model of power quality disturbances, Proceedings of International Conference on Harmonics and Quality of Power, ICHQP, 2018-May, pp. 1–6. DOI: doi.org/10.1109/ICHQP.2018.8378902.

International Energy Agency (IEA), 2024. Global Energy and CO₂ Status Report 2024. Available at: https://www.iea.org/reports/global-energy-and-co2-status-report-2024.

Jiang, Y. and Mao, Z., 2025. A novel carbon emission monitoring method for power generation enterprises based on hybrid transformer model, Scientific Reports, 15(1), pp. 1–16. DOI: doi.org/10.1038/s41598-024-82188-y.

Khan, M. U., Aziz, S. and Usman, A., 2023. XPQRS: Expert power quality recognition system for sensitive load applications, Measurement: Journal of the International Measurement Confederation. Elsevier B.V., 216. DOI: doi.org/10.1016/J.MEASUREMENT.2023.112889.

Khetarpal, P. et al., 2023. Power Quality Disturbances Detection and Classification Based on Deep Convolution Auto-Encoder Networks, IEEE Access. Institute of Electrical and Electronics Engineers Inc., 11, pp. 46026–46038. DOI: doi.org/10.1109/ACCESS.2023.3274732.

Khetarpal, P. and Tripathi, M. M., 2020. A critical and comprehensive review on power quality disturbance detection and classification, Sustainable Computing: Informatics and Systems. Elsevier Inc., 28. DOI: doi.org/10.1016/j.suscom.2020.100417.

Lecun, Y., Bengio, Y. and Hinton, G., 2015. Deep learning, Nature. Nature Publishing Group, 521(7553), pp. 436–444. DOI: doi.org/10.1038/NATURE14539.

Lim, B. et al. 2021. Temporal Fusion Transformers for interpretable multi-horizon time series forecasting, International Journal of Forecasting. Elsevier, 37(4), pp. 1748–1764. DOI: doi.org/10.1016/J.IJFORECAST.2021.03.012.

Ma, J. et al., 2017. Classification of Power Quality Disturbances via Deep Learning, IETE Technical Review, 34(4), pp. 408–415. DOI: doi.org/10.1080/02564602.2016.1196620.

Mahela, O. P., Shaik, A. G. and Gupta, N., 2015. A critical review of detection and classification of power quality events, Renewable and Sustainable Energy Reviews. Elsevier, 41, pp. 495–505. DOI: doi.org/10.1016/j.rser.2014.08.070.

Martinez, R. et al. 2022. Techniques to Locate the Origin of Power Quality Disturbances in a Power System: A Review, Sustainability. Multidisciplinary Digital Publishing Institute, 14(12), p. 7428. DOI: doi.org/10.3390/SU14127428.

Noureddine, A., Rouvoy, R. and Seinturier, L., 2013. A review of energy measurement approaches, Operating Systems Review (ACM), 47(3), pp. 42–49. DOI: doi.org/10.1145/2553070.2553077.

Pan, S. et al., 2024. Classification of Power Quality Disturbances Using Resnet with Channel Attention Mechanism, arXiv preprint.

Perez-Anaya, E. et al., 2024. Methodology for the Detection and Classification of Power Quality Disturbances Using CWT and CNN, Energies, 17(4). DOI: doi.org/10.3390/en17040852.

PNY Technologies Inc., 2018. NVIDIA T4. Available at: https://www.pny.com/nvidia-tesla-t4 (Accessed: 26 August 2025).

Rabczuk, G., Łosiński, J. and Cenian, A., 2020. Description and analysis of methods for calculation of CO2 emission.

SEED - Power Quality Disturbance Dataset, 2023. Available at: https://www.kaggle.com/datasets/sumairaziz/seed-power-quality-disturbance-dataset/data (Accessed: 8 August 2025).

Sekar, K. et al., 2022. An Improved Power Quality Disturbance Detection Using Deep Learning Approach, Mathematical Problems in Engineering, 2022(1). DOI: doi.org/10.1155/2022/7020979.

Singh, G. K., 2009. Power system harmonics research: a survey, Euro. Trans. Electr. Power, 19, pp. 151–172.

Topaloglu, I., 2023. Deep Learning Based a New Approach for Power Quality Disturbances Classification in Power Transmission System, Journal of Electrical Engineering and Technology. Springer Nature Singapore, 18(1), pp. 77–88. DOI: doi.org/10.1007/s42835-022-01177-1.

Wang, J., Xu, Z. and Che, Y., 2019. Power Quality Disturbance Classification Based on Compressed Sensing and Deep Convolution Neural Networks, IEEE Access. IEEE, 7(c), pp. 78336–78346. DOI: doi.org/10.1109/ACCESS.2019.2922367.

Wang, S. and Chen, H., 2019. A novel deep learning method for the classification of power quality disturbances using deep convolutional neural network, Applied Energy. Elsevier, 235, pp. 1126–1140. DOI: doi.org/10.1016/j.apenergy.2018.09.160.

Wen, Q. et al., 2023. Transformers in Time Series: A Survey, IJCAI International Joint Conference on Artificial Intelligence. International Joint Conferences on Artificial Intelligence, 2023-August, pp. 6778–6786. DOI: doi.org/10.24963/IJCAI.2023/759.

Yiǧit, E. et al., 2021. Automatic Detection of Power Quality Disturbance Using Convolutional Neural Network Structure with Gated Recurrent Unit, Mobile Information Systems, 2021(Ml). DOI: doi.org/10.1155/2021/7917500.

Zerveas, G. et al., 2021. A Transformer-based Framework for Multivariate Time Series Representation Learning, Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery, pp. 2114–2124. DOI: doi.org/10.1145/3447548.3467401.

Zhou, H. et al., 2021. Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting, Proceedings of the AAAI Conference on Artificial Intelligence. Association for the Advancement of Artificial Intelligence, 35(12), pp. 11106–11115. DOI: doi.org/10.1609/AAAI.V35I12.17325.