Reliability Analysis of an Inverter at a Solar Power System in Bantul, Yogyakarta, using Random Forest
DOI:
https://doi.org/10.5281/zenodo.18974527Keywords:
renewable energy, Photovoltaic, reliability, predictive maintenance, machine learning, random forest regression.Abstract
Photovoltaic systems are susceptible to various types of failures, such as system faults caused by weather conditions, soiled photovoltaic panels, partial shading, cable damage, short circuits, mechanical failures, and other disturbances. Reliability of photovoltaic systems is critical to ensuring a stable electricity supply. This research used real-time condition-monitoring data from an inverter of a Photovoltaic Power Plant in Bantul, Yogyakarta, Indonesia. In this study, a Random Forest Regression model was employed to predict the photovoltaic system voltage, achieving a coefficient of determination (R²) of 0.5964, indicating that the model explains approximately 59.74% of the variance in the actual data. Failure detection was performed using Residual-Based Anomaly Detection (RBAD), with a 5σ control limit applied to the residuals, resulting in 16 detected failure events over 9,664 operating hours. Based on these results, the Mean Time to Failure (MTTF) of the photovoltaic system was calculated as 593.75 hours, corresponding to a constant failure rate of 0.00168. Reliability analysis showed a gradual degradation over time, with reliability decreasing to 70% at 211 operating hours and 60% at 296 operating hours, indicating the necessity of periodic maintenance.
References
Ahmed, S. I., et al. (2024). Reliability of regression-based hybrid machine learning models for the prediction of solar photovoltaics power generation. Energy Reports, 12, 5009–5023. https://doi.org/10.1016/j.egyr.2024.10.060
Attouri, K., & Hajji, M. (2021). Fault detection in photovoltaic systems using machine learning technique. Proceedings of the 17th International Multi-Conference on Systems, Signals & Devices (SSD 2020).
Baesmat, K. H., Shokoohi, F., & Farrokhi, Z. (2025). SP-RF-ARIMA: A sparse random forest and ARIMA hybrid model for electric load forecasting. Global Energy Interconnection, 8(6), 486–496. https://doi.org/10.1016/j.gloei.2025.04.003
Bagherzadeh, H., et al. (2022). A novel protection scheme to detect, discriminate, and locate electric faults in photovoltaic arrays using a minimal number of measurements. International Journal of Electrical Power and Energy Systems. https://doi.org/10.1016/j.ijepes.2022.108172
Bharath, K., Haque, A., & Khan, M. (2018). Condition monitoring of photovoltaic systems using machine learning techniques. Proceedings of the 2nd IEEE International Conference on Power Electronics, Intelligent Control and Energy Systems (ICPEICES 2018).
Bharath, K., et al. (2019). Fault classification for photovoltaic modules using thermography and machine learning techniques. Proceedings of the IEEE.
Buratti, K., et al. (2019). A machine learning approach to defect parameters extraction: Using random forests to inverse the Shockley-Read-Hall equation.
David, T., et al. (2019). Using large datasets of organic photovoltaic performance data to elucidate trends in reliability between 2009 and 2019. IEEE Journal of Photovoltaics.
Francis, F., & Mohan, M. (2019). ARIMA model based real time trend analysis for predictive maintenance. Proceedings of the Third International Conference on Electronics Communication and Aerospace Technology (ICECA 2019), 735–739.
Gao, Q., et al. (2021). Machine-learning-based intelligent mechanical fault detection and diagnosis of wind turbines. Mathematical Problems in Engineering, 2021, 9915084. https://doi.org/10.1155/2021/9915084
Gunda, T., et al. (2021). A machine learning evaluation of maintenance records for common failure modes in PV inverters.
Helmi, A. F., Herdiani, E. T., & Islamiyati, A. (2025). Residual control chart monitoring for autocorrelated epidemiological data: An application to monthly dengue cases. Communications in Mathematics and Biology and Neuroscience, 2025, 144. https://doi.org/10.28919/cmbn/9426
Khalilnejad, A., et al. (2016). Long term reliability analysis of components of photovoltaic system based on Markov process. Proceedings of the IEEE.
Kurniawan, D. (2022). Pengenalan machine learning dengan Python. PT Elex Media Komputindo.
Muñoz del Río, A., Segovia Ramírez, I., & García Márquez, F. P. (2025). Performance rate analysis in photovoltaic solar plants by machine learning. Advanced Energy and Sustainability Research, 6, 2500144. https://doi.org/10.1002/aesr.202500144
Primartha, R. (2021). Algoritma machine learning. Informatika Bandung.
Saedi, T., et al. (2021). An adaptive machine learning framework for behind-the-meter load/PV disaggregation. IEEE Transactions on Industrial Informatics.
Sayed, A., El-Shimy, M., El-Metwally, M., & Elshahed, M. (2019). Reliability, availability and maintainability analysis for grid-connected solar photovoltaic systems. Energies, 12(7), 1213. https://doi.org/10.3390/en12071213
Shi, X., & Bazi, A. (n.d.). Solar photovoltaic power electronic systems: Design for reliability approach. Advanced Power Electronics and Electric Drives Laboratory (APEDL), University of Connecticut.
Singh, U., Singh, S., Gupta, S., Alotaibi, M. A., & Malik, H. (2025). Forecasting rooftop photovoltaic solar power using machine learning techniques. Energy Reports, 13, 3616–3630. https://doi.org/10.1016/j.egyr.2025.03.005
Suhartanto, T. (2014). Tenaga hibrid (angin dan surya) di Pantai Baru Pandansimo. [Назва журналу], 3.
Syahputra, R., et al. (2020). Analisis indeks keandalan pembangkit listrik tenaga hibrid angin-surya menggunakan metode EENS. Semesta Teknika. https://doi.org/10.18196/st.231259
Tharo, Z., et al. (2014). Pembangkit listrik hybrid tenaga surya dan angin sebagai sumber alternatif menghadapi krisis energi fosil di Sumatera.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Patricia Fitrianingtyas, Dimas Fajarisandi
This work is licensed under a Creative Commons Attribution 4.0 International License.