Improving Estimation of Parameters in Photovoltaic Models Using Two-Level Layered Physics-Informed Neural Networks

Abstract

Accurate estimation of parameters in photovoltaic models is essential to improve system monitoring, control, and diagnostics. In this study, a novel two-level layered physics-informed neural network (PINN) architecture is proposed to estimate the parameters irradiance ($G$) and temperature ($T$), and junction capacitance ($C_{j0}$) in a dynamic single-diode PV model. In case no noise affects the PV current and voltage waveforms, the proposed method achieves errors equal to 0.25% for $G$, 1.5% for $T$, and 2.1% for $C_{j0}$. Compared to traditional optimization methods, the two-level layered PINN shows a better performance, particularly in learning the nonlinear behavior of $C_{j0}$. Sensitivity analysis under additive Gaussian noise (0% –5% ) confirms the robustness of the approach, with a slight increase of the identification error. The results confirm the effectiveness of incorporating physical knowledge into neural networks for robust and reliable parameter estimation in dynamic photovoltaic systems.