Answers are grounded in this paper and cite their sources.
This work reveals a self-supervised machine learning method to estimate open-circuit voltage in photovoltaic systems, suggesting improved fault detection.
In this work, we present a machine learning (ML) approach that integrates physics‐based knowledge with data‐driven techniques to estimate the open‐circuit voltage () of photovoltaic (PV) systems. This self‐supervised approach allows the detection of anomalies in operating systems, enabling the identification of potential faults and degradation related to without requiring labelled data. Deviations in values are detected by analysing the measurements recorded in the supervisory control and data acquisition (SCADA) system. This analysis is performed by a combination of clustering and regression algorithms. The proposed approach is validated on three different PV installations, showcasing its ability to detect variations in open‐circuit voltage and to predict performance degradation. The proposed method achieves an ‐squared (r2) value larger than 0.9 when trained on experimental data from three distinct PV systems. Moreover, it estimates from SCADA data with an average error below 5% compared with – curve measurements. The results of this study demonstrate that physics informed ML techniques can significantly enhance the performance and reliability of PV systems, enabling early fault detection and degradation forecasting.
No takes yet. Share an insight, caveat, or question.
Riaño et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: