Deep Neural Network MPPT-based PV Water Pumping With PMSM Drive

This article presents a field-oriented control (F<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">i</inf>OC) for a permanent. magnet synchronous motor (PMS Motor), The boost converter is controlled using deep learning Maximum Power Point Tracking (Maximum PPT). The best ways to extract the most power possible from photovoltaic (PV) modules are still being researched. The Maximum PPT technique matches the load resistance to the PV module’s characteristic resistance, which varies with temperature and solar irradiation, in order to run the module at its maximum power point. The widely used techniques are perturbation and Observe (P and O) and Incremental conductance (IC) serves as the basis for other sophisticated approaches. A new approach is suggested that uses a deep neural network to figure out the ideal perturbation size to get to the Maximum PPT by comparing the above methods. Using the toolbox of Deep learning from MATLAB, a Deep neural network-based Maximum PPT solar-powered system for pumping water with PMS Motor drive was developed in the MATLAB domain. The suggested system’s performance is obtained under conditions of considerable variation in solar radiation and PMS Motor speed.