XAI Implementation for Inverter-Level Underperformance Analysis of the PV Power Plant from Actual Operational Data
DOI:
https://doi.org/10.26418/elkha.v18i1.104850Keywords:
photovoltaic power plant, inverter performance, energy loss analysis, XGBoost, SHAP, explainable machine learningAbstract
Photovoltaic (PV) power plants installed on uneven terrain often experience spatially non-uniform operating conditions that lead to performance disparities among inverters, which may not be detected through conventional system-level monitoring. This study presents an inverter-level performance analysis of the Nusa Penida PV power plant using one year of operational data with a 30-minute resolution. A data-driven framework integrating Extreme Gradient Boosting (XGBoost) classification and explainable artificial intelligence was developed to detect underperforming inverters and interpret the contributing factors affecting system performance. The analysis identified significant performance variations among the 18 inverters, with seven units categorized as underperforming based on a relative performance ratio threshold of 0.80 compared to the highest-performing inverter at the same timestamp. The proposed XGBoost classification model achieved an AUC of approximately 0.79 on the test dataset, indicating reliable discrimination between normal and underperforming inverter conditions. Further analysis shows that the detected underperformance corresponds to annual energy losses ranging from approximately 81,000 kWh to 119,000 kWh per inverter when compared with the best-performing reference unit. Explainable analysis using SHapley Additive exPlanations (SHAP) reveals that irradiance and temporal variables are the dominant contributors affecting inverter performance, while persistent negative feature contributions in several inverters indicate location-related constraints beyond natural environmental variability. These results demonstrate that inverter-level monitoring combined with interpretable machine learning provides deeper diagnostic insight than aggregated performance indicators and can support more effective identification of structural performance limitations in PV power plants installed on non-uniform terrain.References
D. C. Jordan and S. R. Kurtz, “PV degradation rates—An analytical review,” Prog. Photovolt.: Res. Appl., vol. 21, no. 1, pp. 12–29, 2013.
B. Marion et al., “Performance parameters for grid-connected PV systems,” Solar Energy, vol. 86, no. 9, pp. 2679–2694, 2012.
G. Makrides et al., “Potential of photovoltaic systems in tropical regions,” Energy, vol. 36, no. 2, pp. 1202–1210, 2011.
A. Pillai et al., “Inverter-level performance monitoring of large-scale photovoltaic plants,” Solar Energy, vol. 240, pp. 1–12, 2022.
A. Mellit, S. Kalogirou, S. Shaari, H. Salhi, and A. Hadj Arab, “Artificial intelligence techniques for photovoltaic applications: A review,” Renew. Sustain. Energy Rev., vol. 33, pp. 44–64, 2014.
T. Chen and C. Guestrin, “XGBoost: A scalable tree boosting system,” in Proc. 22nd ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining (KDD), 2016, pp. 785–794.
S. M. Lundberg and S.-I. Lee, “A unified approach to interpreting model predictions,” in Proc. 31st Conf. Neural Information Processing Systems (NeurIPS), 2017.
H. Li et al., “Explainable machine learning for photovoltaic power prediction,” Appl. Energy, vol. 336, p. 120796, 2023.
M. G. Deceglie, “Perspective: Performance loss rate in PV systems,” Solar RRL, vol. 7, no. 3, 2023.
A. Dolara, R. Faranda, and S. Leva, “Aging effects on inverter efficiency in photovoltaic plants,” IEEE Trans. Power Electron., vol. 30, no. 7, pp. 3983–3991, 2015.
S. B. Kouro et al., “Power electronic reliability in photovoltaic inverters,” IEEE Trans. Ind. Electron., vol. 68, no. 6, pp. 5412–5422, 2021.
H. Sharadga, S. Hajimirza, and R. Balog, “Time series forecasting of solar power generation,” Renewable Energy, vol. 151, pp. 115–124, 2020.
M. T. Ribeiro, S. Singh, and C. Guestrin, “Why should I trust you? Explaining the predictions of any classifier,” in Proc. 22nd ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining (KDD), 2016, pp. 1135–1144.
A. Molnar, Interpretable Machine Learning. 2nd ed., 2022.
M. A. Hossain et al., “Hybrid deep learning model for renewable energy forecasting,” J. Cleaner Prod., vol. 299, p. 126900, 2021.
S. M. Hossain, M. Mekhilef, and R. Saidur, “Machine learning-based fault detection in photovoltaic systems: A comprehensive review,” Renew. Sustain. Energy Rev., vol. 168, p. 112786, 2022.
Y. Wang, L. Zhao, and H. Chen, “Data-driven performance assessment of large-scale photovoltaic plants using inverter-level monitoring,” Appl. Energy, vol. 336, p. 120796, 2023.
F. R. Islam, K. A. Mamun, and M. Hossain, “Explainable artificial intelligence for renewable energy systems: A review,” Energy Reports, vol. 9, pp. 4760–4780, 2023.
J. Li and H. Yang, “Impact of terrain-induced irradiance variability on photovoltaic system performance,” Solar Energy, vol. 246, pp. 1–12, 2022.
A. Kumar and B. Singh, “Long-term operational performance evaluation of utility-scale photovoltaic plants,” IEEE Trans. Sustain. Energy, vol. 14, no. 2, pp. 1234–1245, 2023.
M. Kuzlu, U. Cali, V. Sharma, and Ö. Güler, “Gaining insight into solar photovoltaic power generation forecasting utilizing explainable artificial intelligence tools,” IEEE Access, vol. 8, pp. 187033–187045, 2020.
M. Al-Shammari et al., “An interpretable deep learning model for solar power generation forecasting in a grid-connected hybrid solar system,” IEEE J. Photovolt., vol. 12, no. 3, pp. 827–838, 2022.
X. Zhang et al., “CEEMDAN-LSTM-XGBoost based multi-step short-term power forecasting for offshore photovoltaic systems,” 2026.
Z. Song, S. Cao, and H. Yang, “An interpretable framework for modeling global solar radiation using tree-based ensemble machine learning and Shapley additive explanations methods,” Appl. Energy, vol. 364, p. 123238, 2024.
B. Ren, Q. Wang, N. Zhou, and S. Mekhilef, “Development and validation of interpretable machine learning models for photovoltaic panel temperature prediction,” Expert Syst. Appl., vol. 296, p. 128952, 2026.
A. Dinakar et al., “Explainable machine learning models for predicting current and voltage in photovoltaic systems,” Energy Convers. Manage.: X, vol. 30, p. 101627, 2026.
M. Huang et al., “Materials-informed long-term photovoltaic energy yield prediction: Unveiling the dynamic degradation mechanisms of anti-reflective coatings via explainable machine learning,” Renewable Energy, vol. 260, p. 125172, 2026.
A. Abdellatif et al., “SHapley Additive exPlanations-guided rule-based energy management: Bridging machine learning interpretability and adaptive control strategies,” Renewable Energy Focus, vol. 56, p. 100779, 2026.
X. Gao et al., “Surface albedo evaluation in an arid-region photovoltaic power plant through field spectral radiometry and explainable machine learning,” Solar Energy, vol. 299, p. 113761, 2025.
J. Liu, C. Peng, and J. Zhang, “Understanding the relationship between rural morphology and photovoltaic (PV) potential using SHAP values,” Appl. Energy, vol. 380, p. 125091, 2025.
S. Bordihn et al., “Machine learning based identification and classification of field-operation caused solar panel failures observed in electroluminescence images,” IEEE J. Photovolt., vol. 12, no. 3, 2022.
P. Xi et al., “Online fault diagnosis for photovoltaic arrays based on Fisher discrimination dictionary learning for sparse representation,” IEEE Access, vol. 9, pp. 12345–12358, 2021.
A. Apaza-Pinto et al., “Supervised machine learning techniques for the prediction of the state of charge of batteries in photovoltaic systems,” IEEE Access, vol. 10, pp. 45678–45690, 2022.
M. Alagarsamy et al., “XAI-based photovoltaic energy management framework for smart cities,” IEEE Access, vol. 13, 2025.
Downloads
Additional Files
Published
Issue
Section
License
Copyright (c) 2026 ELKHA : Jurnal Teknik Elektro
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
1. Proposed Policy for Journals That Offer Open Access
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
2. Proposed Policy for Journals That Offer Delayed Open Access
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication, with the work [SPECIFY PERIOD OF TIME] after publication simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
