利用双层物理信息神经网络改进光伏模型参数估计

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.