Abstract
Building integrated photovoltaic (BIPV), based on tandem PV cells, is considered a new alternative for combining solar energy with buildings. Accurately predicting the BIPV-harvested annual output energy (Eout,annual) is crucial for evaluating the BIPV performance. Machine learning (ML) is a potential candidate for solving such a problem without the time-consuming process of experimental investigations. This contribution proposes an artificial neural network (ANN) to predict the Eout,annual of 4-terminal perovskite/silicon (psk/Si) PV cells under realistic environmental conditions. The input variables of the proposed model consist of the input solar irradiance (Pin), incident light's angle (Ain), the PV module's temperature (Tmod), the psk absorber's thickness (Thpsk), and the psk absorber's bandgap (Bpsk). The input data were received from the simulated results. This work also evaluates the degree of importance of each input variable and optimizes the architecture of the ANN using the surrogate algorithm before predictions. The optimized ANN-3 (three hidden layers) model shows superior performance indicators, including a mean squared error of MSE = 0.02283, correlation coefficient R = 0.99999, and Willmott's index of agreement Iw = 0.99999. Consequently, the predicted highest Eout,annual at Bpsk of 1.71 eV is 297.73, 115.01, 193.98, and 97.6 kWh/m(2) for the rooftop, east, south, and west facades, respectively.