Abstract
The study was conducted to develop a mathematical model of photovoltaic systems using artificial neural networks. A mathematical model of the photovoltaic system was established, a simulation process was implemented considering key parameters, and a maximum power point tracking method was applied to improve the efficiency of the system. In this research, a mathematical model of photovoltaic system based on artificial neural networks was developed and tested to improve the efficiency of solar panels. The model showed high accuracy in predicting the maximum power point under varying environmental conditions such as illumination and temperature. Analysis of the data demonstrated that the use of neural networks for maximum power point tracking significantly reduces energy losses compared to traditional tracking methods. Experimental results confirmed that the proposed approach provides more stable and accurate detection of the maximum power point in real time. The findings showed that the implementation of such a system could significantly improve the overall performance of PV plants, especially under erratic solar conditions, making it promising for applications in different climatic zones. In addition, the model was shown to be robust to changes in input data parameters, making it adaptive to different types of solar panels and operating conditions. It was also found that the neural network-based system reduces PV plant operation and maintenance costs by minimizing the need for manual calibration and monitoring. The resulting model will improve the accuracy and efficiency of maximum power tracking of solar panels under varying environmental conditions