STC Short-Circuit Current Prediction and I-V Simulation of Colored BIPV Modules With Machine Learning and One-Diode Equivalent Circuit Models

Abstract

Colored photovoltaic (PV) modules offer improved aesthetics at the cost of electrical performance loss. Here, we demonstrate a hybrid approach combining experiments, machine learning, and equivalent-circuit model to predict and simulate <italic>I&#x2013;V</italic> parameters of colored crystalline-silicon PV modules. First, to predict the short-circuit current for different colors and opacity levels, three models&#x2014;multiple linear regression (MLR), optimized support vector regression (SVR), and optimized Gaussian process regression (GPR)&#x2014;are trained and evaluated with a ten-fold cross validation. The MLR model shows an MAE &#x003D; 3.58 and an RMSE &#x003D; 5.17. The accuracy could be further improved with the more advanced models, i.e., an optimized SVR (MAE &#x003D; 0.22, RMSE &#x003D; 0.24) or an optimized GPR (MAE &#x003D; 0.13, RMSE &#x003D; 0.17). Following, by taking the predicted short-circuit current values as inputs into a one-diode equivalent circuit model, <italic>I&#x2013;V</italic> curves of two multicolored modules are simulated; and information such as module power <italic>P</italic>_mpp and current mismatch loss are extracted. There is a twofold advantage of implementing our approach: first, it serves as an efficient design space exploration methodology for a wide parameter space (e.g., colors), i.e., evaluating the PV performance for new colors without samples fabrication, thus saving time and resources; and second, it guides architects, designs, and engineers in color&#x002F;design selection to achieve a balance between aesthetics and engineering considerations.