The growing competitiveness of solar photovoltaic (PV) panels as a sustainable energy option has led to an increase in the installation of PV panels in recent pass. The power output of solar panels highly depends on various environmental factors such as wind, humidity, solar radiation, and temperature. Under adverse weather conditions or unfavorable conditions, it is difficult for solar panels to provide the best efficiency. Understanding the anticipated power generation of solar panels in advance is crucial for the proper configuration and optimization of their potential. This study introduces an approach to anticipate the power output of solar panels by employing artificial neural network techniques or algorithms, while considering diverse environmental variables, such as wind, humidity, and temperature. We created artificial neural network models using the NN tool in MATLAB. Our datasets were collected from www.github.com . A comparative analysis of various artificial neural network models conducts in this article based on five environmental factors: temperature of the air, solar radiation, humidity relative to the air, and direction and speed of the wind solar radiation. The experimental findings indicate that these features serve as effective predictors for estimating the power output of solar panels.