Impact of absolute and relative humidity on the performance of mono and poly crystalline silicon photovoltaics; applying artificial neural network

The impacts of the ambient absolute and relative humidity on the performance of a photovoltaic (PV) solar module are investigated in details here. Using the experimental data recorded during a year as inputs, the artificial neural network is employed to develop models to predict voltage and current based on the effective parameters, including ambient temperature and relative humidity, as well as the wind velocity and irradiance, and having developed and validated the models, a comprehensive parametric study is conducted. The parametric study is performed to find the impacts of absolute and relative humidity on the voltage, current, power, and efficiency, as the main characteristics of a solar module. A mono and a poly crystalline solar modules with the same capacity and almost the same dimensions are considered and compared together. The results show that all the characteristics have a downward trend when absolute and relative humidity increase. Moreover, both the behavior and changes for the absolute humidity are found the same as the relative humidity. In addition, the lowest level of dependency is observed for voltage the of monocrystalline module. It has 12.2% decrease in the relative humidity range of 10–50%. By contrast, both generated power and efficiency of the polycrystalline module change 46.3% in the same range and have the highest sensitivity level. Moreover, in general, the poly crystalline type is found more sensitive to the relative humidity than the mono type.