DESIGN AND IMPLEMENTATION OF FUZZY MACHINE LEARNING BASED CONTROLLER FOR MAXIMUM POWER POINT TRACKING OF A PV FARM SYSTEM

Abstract

Solar energy systems are considered one of the most important systems that researchers have been developing due to their importance in generating electrical energy, but these systems suffer from a fundamental problem, which is the dependence of the power extracted from solar panels on radiation strength and temperature, and they are by nature variable. Therefore, in this research a simulation was made to design artificial intelligence controllers such as fuzzy logic or artificial neural networks to follow the maximum power point extracted from these systems during sudden changes in temperature and solar radiation by calculating the voltage corresponding to the maximum power and then controlling the DC – DC Converter to obtain this voltage. These controllers are divided into two types, the first type is based on machine learning technology and aims to obtain the voltage value corresponding to the maximum power, while the second type aims to control the DC-DC converter to ensure the required voltage is reached. The proposed controllers were tested by modeling them with a solar cell system and DC-DC converters using the MATLAB program under different temperatures and radiation levels. The tests included actual temperatures and radiation levels registered in Cairo. The results have demonstrated the effectiveness and ability of the proposed first type controller in