<![CDATA[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.]]>
Copyrights © 2026
