Maximum Powerpoint Tracking by ANN under Conditions of Uniform Irradiance and Partial Shading

Solar photovoltaic (PV) systems are becoming more and more popular since they convert solar radiation directly into clean, sustainable electricity. While it has many benefits, there are also some drawbacks, such as its reliance on environmental factors. If the solar panel does not receive uniform radiation, the electricity it produces drops. Partial shadowing situations occur when a PV module is occasionally partially obscured by neighbouring structures, moving clouds, etc., reducing the power output of solar panels. It significantly lowers the system's power output. Coupled to the photovoltaic module, the recommended LUO converters make it possible to follow the maximum power point even when the module is partially shaded, using procedures that include continuous duty cycle change. Approaches that monitor the maximum power point under situations of partial shadow have been presented as a solution to this problem. These methods include continuous duty cycle change. In these configurations, the suggested LUO converters are wired up to the PV modules in order to permit the highest possible output voltage in any given circumstance. The suggested system has been updated to include a cutting-edge method known as Artificial Neural Network-based Maximum Power Point Tracking (ANN-MPPT), which can track the Maximum Power Point even when there are several local maxima present. The suggested method tracks Maximum Power Point (MPP) by continuously varying the duty cycle of the converter without using expensive parts like signal converters and microprocessors, making the system more compact. The converter's objective is to deliver input currents with a tolerable harmonic content in a grid interface while operating at unity power factor. Finally, we will run a number of numerical simulations using the MATLAB 2021a/Simulink programme to test the suggested controls.