Simulation-Based CNN-LSTM Fault Detection Framework for Grid-Connected Solar PV Systems

Dr.P.Aravindan; Saravanaraj.M

doi:10.65379/IJAEMS/V2-I2-08Jun2026-P78

Back

Research Article Matrix Node

Simulation-Based CNN-LSTM Fault Detection Framework for Grid-Connected Solar PV Systems

Author(s): Dr.P.Aravindan, Saravanaraj.M

Volume RegistryVolume 2

Issue PeriodIssue 02

Published Date08 Jun 2026

DOI Identifier🔗 10.65379/IJAEMS/V2-I2-08Jun2026-P78

Abstract

The current study proposes an innovative simulation-based deep learning architecture for fault detection in solar photovoltaic (PV) systems connected to a grid system. A computerized PV system model was created in MATLAB Simulink to obtain data sets depending on irradiance level, temperature level, and faults. Data sets were normalized and divided into smaller segments using the sliding window technique and then fed to train the hybrid CNN-LSTM network. While CNN is responsible for spatial feature extraction in electric parameters, LSTM focuses on temporal feature extraction. The combination of CNN-LSTM model allows for reliable fault classification, including shading fault, open circuit fault, short circuit fault, and degradation fault. The CNN-LSTM network attained a classification accuracy of up to 97-98%, exhibiting high levels of robustness and versatility in fault detection in solar PV systems. The CNN-LSTM system design represents a breakthrough in the area of PV intelligent faults detection.

Keywords

Grid-connected solar PV systems Fault detection CNN-LSTM hybrid model Simulation framework IoT -based monitoring Deep learning analytics Smart grid reliability.

References (14)

V. Veerasamy et al., "LSTM Recurrent Neural Network Classifier for High Impedance Fault Detection in Solar PV Integrated Power System," in IEEE Access, vol. 9, pp. 32672- 32687, 2021, doi: https://doi.org/10.1109/ACCESS.2021.3060800
M. Alrifaey et al., "Hybrid Deep Learning Model for Fault Detection and Classification of Grid-Connected Photovoltaic System," in IEEE Access, vol. 10, pp. 13852-13869, 2022, doi: https://doi.org/10.1109/ACCESS.2022.3140287
A. S. Alhanaf, M. Farsadi and H. H. Balik, "Fault Detection and Classification in Ring Power System With DG Penetration Using Hybrid CNN- LSTM," in IEEE Access, vol. 12, pp.59953- 59975,2024,doi:https://doi.org/10.1109/ACCESS.2024.339416
D. P. Patel, I. Prashant Pathak, D. Roach and N. Yilmazer, "Robust Deep Learning Models for Fault Detection in Grid-tied Solar Inverters: A Comparative Study of LSTM, Bi-LSTM, and CNN-LSTM Architectures," 2026 IEEE Green Technologies Conference (GreenTech), Boulder, CO, USA, 2026, pp. 476-481, doi: https://doi.org/10.1109/GreenTech68285.2026.11471570
Amiri, A. F., Kichou, S., Oudira, H., Chouder, A., & Silvestre, S. (2023). Fault Detection and Diagnosis of a Photovoltaic System Based on Deep Learning Using the Combination of a Convolutional Neural Network (CNN) and Bidirectional Gated Recurrent Unit (Bi-GRU). Sustainability, 16(3), 1012. https://doi.org/10.3390/su16031012
Vadlamudi, B., & T, A. (2024). Optimized Hybrid CNN-LSTM Based Islanding Detection of Solar-Wind Power System. Electric Power Components and Systems, 52(3), 337– 355. https://doi.org/10.1080/15325008.2023.222033 3 7. Özcanlı, A. K., & Baysal, M. (2021). A novel Multi-LSTM based deep learning method for islanding detection in the microgrid. Electric Power Systems Research, 202, 107574. https://doi.org/10.1016/j.epsr.2021.107574
M. A. Khan, A. Haque and V. S. B. Kurukuru, "Machine Learning Based Islanding Detection for Grid Connected Photovoltaic System," 2019 International Conference on Power Electronics, Control and Automation (ICPECA), New Delhi, India, 2019, pp. 1-6, doi: https://doi.org/10.1109/ICPECA47973.2019.8975614
B. Roy et al., "Deep Learning Based Relay for Online Fault Detection, Classification, and Fault Location in a Grid-Connected Microgrid," in IEEE Access, vol. 11, pp. 62674- 62696, 2023, doi: https://doi.org/10.1109/ACCESS.2023.3285768
Ramasamy, S., & Perumal, M. (2021). CNN-based deep learning technique for improved H7 TLI with grid-connected photovoltaic systems. International Journal of Energy Research, 45(14), 19851 -19868. https://doi.org/10.1002/er.7030
M. M. Rahman, M. S. Hossain, M. S. I. Talukder and M. N. Uddin, "Transformerless Six- Switch (H6)-Based Single-Phase Inverter for Grid-Connected Photovoltaic System With Reduced Leakage Current," in IEEE Transactions on Industry Applications, vol. 58, no. 1, pp. 974- 985, Jan. -Feb. 2022, doi: https://doi.org/10.1109/TIA.2021.3131295
K. Ullah et al., "Short-Term Load Forecasting: A Comprehensive Review and Simulation Study With CNN-LSTM Hybrids Approach," in IEEE Access, vol. 12, pp. 111858- 111881, 2024, doi: https://doi.org/10.1109/ACCESS.2024.3440631
S. H. Rafi, Nahid-Al-Masood, S. R. Deeba and E. Hossain, "A Short-Term Load Forecasting Method Using Integrated CNN and LSTM Network," in IEEE Access, vol. 9, pp. E-ISSN: 3107-5843 International Journal of Advanced Engineering and Management System Volume 02, Issue 02, April-June 2026, pp. 67 - 77 32436-32448, 2021, doi: https://doi.org/10.1109/ACCESS.2021.3060654
Zhang, S., Chen, R., Cao, J., & Tan, J. (2023). A CNN and LSTM-based multi-task learning architecture for short and medium-term electricity load forecasting. Electric Power Systems Research, 222, 109507. https://doi.org/10.1016/j.epsr.2023.109507
Karthikeyan, G., & Jagadeeshwaran, A. (2024). Enhancing Solar Energy Generation: A Comprehensive Machine Learning-Based PV Prediction and Fault Analysis System for Real- Time Tracking and Forecasting. Electric Power Components and Systems, 52(9), 1497– 1512.https://doi.org/10.1080/15325008.2023.229 3947

Dr.P.Aravindan and Saravanaraj.M, "Simulation-Based CNN-LSTM Fault Detection Framework for Grid-Connected Solar PV Systems," Int. J. Adv. Eng. Manag. Syst., vol. 2, no. 2, pp. 353-363, 2026. doi: 10.65379/IJAEMS/V2-I2-08Jun2026-P78.

Simulation-Based CNN-LSTM Fault Detection Framework for Grid-Connected Solar PV Systems

Abstract

Keywords

References (14)

Format Citation Record