What question did this study set out to answer?

The aim is to develop a deep learning framework for predicting performance losses in photovoltaic systems due to various factors.

February 11, 2026Open Access

Deep Learning-Based Detection and Forecasting of Performance Losses in Solar PV Systems Using Multi-Sensor Data

Key Points

The aim is to develop a deep learning framework for predicting performance losses in photovoltaic systems due to various factors.
Utilized multi-sensor time-series data to assess performance degradation.
Developed a hybrid CNN and LSTM model to incorporate both local and long-term degradation dynamics.
Evaluated model performance using a synthetically generated dataset that reflects real PV measurements.
The proposed CNN–LSTM model significantly outperformed baseline models such as linear regression and XGBoost.
Achieved reductions in mean absolute error (MAE) and normalized root mean square error (RMSE).
Confirmed stable error performance and effective temporal generalization for predictive maintenance applications.

Abstract

Photovoltaic (PV) systems are subject to nonlinear performance degradation caused by operational and environmental factors, which limits reliable energy production. Most existing studies focus on power output forecasting and fail to isolate intrinsic efficiency losses from meteorological variability. This study proposes a degradation-aware deep learning framework for predicting PV performance loss using multi-sensor time-series data. Performance degradation is formulated as a reference-based performance loss ratio derived from the deviation between observed power output and an ideal physics-informed reference model. A hybrid convolutional neural network (CNN) and long short-term memory (LSTM) architecture is employed to jointly capture local feature representations and long-term temporal degradation dynamics. Model evaluation is conducted using a synthetically generated yet physically consistent dataset, informed by real PV measurements to ensure real-world relevance. Experimental results demonstrate that the proposed CNN–LSTM model outperforms baseline approaches, including persistence, linear regression, and XGBoost, particularly in terms of mean absolute error (MAE) and normalized root mean square error (RMSE). Additional analyses confirm stable error behavior and temporal generalization, highlighting the suitability of the proposed approach for degradation-aware performance monitoring and predictive maintenance in PV systems.

Demander à l'IA

Bookmark

View Full Paper