Machine Learning for Predictive Power Quality Maintenance in Modern Power Grids

International Journal of Electrical and Electronics Engineering

© 2026 by SSRG - IJEEE Journal

Volume 13 Issue 1

Year of Publication : 2026

Authors : S. Parthiban, N R Govinthasamy, Venkatesh Kumar S, S D Vijayakumar

10.14445/23488379/IJEEE-V13I1P113

How to Cite?

S. Parthiban, N R Govinthasamy, Venkatesh Kumar S, S D Vijayakumar, "Machine Learning for Predictive Power Quality Maintenance in Modern Power Grids," SSRG International Journal of Electrical and Electronics Engineering, vol. 13,  no. 1, pp. 132-141, 2026. Crossref, https://doi.org/10.14445/23488379/IJEEE-V13I1P113

Abstract:

The challenge of ensuring good quality of power in contemporary smart grids has become more complicated with the erratic nature of renewable sources, nonlinear loads, and the changing trend of demand. It discusses a machine learning-based predictive power quality maintenance framework that incorporates a hybrid Long Short-Term Memory (LSTM) and Random Forest (RF) model. The system compares voltage, current, and harmonic data to forecast faults before they occur. The model proposed had a prediction accuracy of 98.3%, a Mean Absolute Percentage Error (MAPE) of 1.84%, and a Root Mean Square Error (RMSE) of 0.042 kV, which was better than the traditional approaches. Moreover, it minimized the maintenance expenses by 31.6% and increased grid reliability by 28.9%. The model was confirmed to be able to carry out real-time analysis and decision support using simulation on MATLAB. These findings indicate that predictive maintenance based on Machine Learning can be used to improve the efficiency of operations, reduce downtime, and improve the resilience of modern power grids.

Keywords:

Long Short-Term Memory, Power Quality, Mean Absolute Percentage Error, Root Mean Square Error, Phasor Measurement Unit, Particle Swarm Optimization.

References:

[1] Fatema A. Albalooshi, and M.R. Qader, “Deep Learning Algorithm for Automatic Classification of Power Quality Disturbances,” Applied Sciences, vol. 15, no. 3, pp. 1-19, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Ravikumar Chinthaginjala et al., “Hybrid AI and Semiconductor Approaches for Power Quality Improvement,” Scientific Reports, vol. 15, no. 1, pp. 1-18, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Uvesh Sipai et al., “Deep Transfer Learning Approach for the Classification of Single and Multiple Power Quality Disturbances,” Scientific Reports, vol. 15, no. 1, pp. 1-19, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[4] David Olojede, Stephen King, and Ian Jennions, “Application of Machine Learning in Power Grid Fault Detection and Maintenance,” Energy Informatics, vol. 8, no. 1, pp. 1-36, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Shuangquan Yang, Tao Shan, and Xiaomei Yang, “Interpretable DWT-1DCNN-LSTM Network for Power Quality Disturbance Classification,” Energies, vol. 18, no. 2, pp. 1-19, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Hao Bai et al., “Power Quality Disturbance Classification Strategy based on Fast S-Transform and an Improved CNN-LSTM Hybrid Model,” Processes, vol. 13, no. 3, pp. 1-20, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Dhanunjayudu Nasika et al., “Real-Time PQD Detection, Classification and Localization using Recurrence Plots and EfficientNet-SE in Solar Integrated IEEE 13-Bus System,” Scientific Reports, vol. 15, no. 1, pp. 1-17, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Muhammad Hassan Anwar et al., “Detection and Classification of Power Quality Disturbances: Vision Transformers vs CNN,” AIMS Energy, vol. 13, no. 5, pp. 1052-1075, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Lei Chen et al., “Power Quality Disturbances Identification based on Deep Neural Network Model of Time-Frequency Feature Fusion,” Electric Power Systems Research, vol. 231, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Poras Khetarpal et al., “Power Quality Disturbance Signal Segmentation and Classification based on Modified BI-LSTM with Double Attention Mechanism,” IET Generation, Transmission and Distribution, vol. 18, no. 1, pp. 50-62, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Yu Shen et al., “A Risk Warning Method for Steady-State Power Quality based on VMD-LSTM and a Fuzzy Model,” Heliyon, vol. 10, no. 9, pp. 1-15, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Le Gao et al., “Classification Strategy for Power Quality Disturbances based on Variational Mode Decomposition Algorithm and Improved Support Vector Machine,” Processes, vol. 12, no. 6, pp. 1-17, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Arvind R. Singh et al., “Machine Learning-based Energy Management and Power Forecasting in Grid-Connected Microgrids with Multiple Distributed Energy Sources,” Scientific Reports, vol. 14, no. 1, pp. 1-23, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Manuela Panoiu, and Caius Panoiu, “Hybrid Deep Neural Network Approaches for Power Quality Analysis in Electric Arc Furnaces,” Mathematics, vol. 12, no. 19, pp. 1-30, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Nuno M. Rodrigues, Fernando M. Janeiro, and Pedro M. Ramos, “Deep Learning for Power Quality Event Detection and Classification based on Measured Grid Data,” IEEE Transactions on Instrumentation and Measurement, vol. 72, pp. 1-11, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Zhanbei Tong et al., “A Power Quality Disturbances Classification Method based on Multi-Modal Parallel Feature Extraction,” Scientific Reports, vol. 13, no. 1, pp. 1-10, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Jiajun Cai, Kai Zhang, and Hui Jiang, “Power Quality Disturbance Classification based on Parallel Fusion of CNN and GRU,” Energies, vol. 16, no. 10, pp. 1-12, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Carlos Alberto Iturrino Garcia et al., “Power Quality Analysis based on Machine Learning Methods for Low-Voltage Electrical Distribution Lines,” Energies, vol. 16, no. 9, pp. 1-28, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Indu Sekhar Samanta et al., “A Comprehensive Review of Deep-Learning Applications to Power Quality Analysis,” Energies, vol. 16, no. 11, pp. 1-31, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Zakarya Oubrahim et al., “Power Quality Disturbances Characterization using Signal Processing and Pattern Recognition Techniques: A Comprehensive Review,” Energies, vol. 16, no. 6, pp. 1-41, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Fatma Zohra Dekhandji et al., “Detection and Classification of Power Quality Disturbances using LSTM,” Engineering Proceedings, vol. 29, no. 1, pp. 1-7, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Ramya Kuppusamy, Srete Nikolovski, and Yuvaraja Teekaraman, “Review of Machine Learning Techniques for Power Quality Performance Evaluation in Grid-Connected Systems,” Sustainability, vol. 15, no. 20, pp. 1-29, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[23] M. Dhanapal et al., “Enrichment of Power Quality Analysis using Machine Learning Algorithm,” 2023 3rd International Conference on Innovative Mechanisms for Industry Applications (ICIMIA), Bengaluru, India, pp. 1028-1031, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Joaquín E. Caicedo et al., “A Systematic Review of Real-Time Detection and Classification of Power Quality Disturbances,” Protection and Control of Modern Power Systems, vol. 8, no. 1, pp. 1-37, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Kavaskar Sekar et al., “An Improved Power Quality Disturbance Detection using Deep Learning Approach,” Mathematical Problems in Engineering, vol. 2022, no. 1, pp. 1-12, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[26] Grazia Todeschini, Karan Kheta, and Cinzia Giannetti, “An Image-based Deep Transfer Learning Approach to Classify Power Quality Disturbances,” Electric Power Systems Research, vol. 213, pp. 1-9, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[27] Raul V.A. Monteiro, Raoni F.S. Teixeira, and Arturo S. Bretas, “Power Quality Disturbances Diagnosis: A 2D Densely Connected Convolutional Network Framework,” Electric Power Systems Research, vol. 212, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[28] Alper Yılmaz, Ahmet Küçüker, and Gökay Bayrak, “Automated Classification of Power Quality Disturbances in a SOFC and PV-based Distributed Generator using a Hybrid Machine Learning Method with High Noise Immunity,” International Journal of Hydrogen Energy, vol. 47, no. 45, pp. 19797-19809, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[29] Soumya Ranjan Das et al., “Application of Artificial Intelligent Techniques for Power Quality Improvement in Hybrid Microgrid System,” Electronics, vol. 11, no. 22, pp. 1-19, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[30] R. Pavithra Guru, and V. Vaithianathan, “An Efficient VLSI Circuit Partitioning Algorithm based on Satin Bowerbird Optimization (SBO),” Journal of Computational Electronics, vol. 19, no. 3, pp. 1232-1248, 2020
[CrossRef] [Google Scholar] [Publisher Link]