Solar PWM inverter using artifical neural network

The output characteristics of photovoltaic arrays are nonlinear and change with the cell´s temperature and solar radiation. Maximum power point tracking (MPPT) methods are used to maximize the PV array output power by tracking continuously the maximum power point (MPP). Among all MPPT methods existing in the literature, perturb and observe (P&O) is the most commonly used for its simplicity and ease of implementation; however, it presents drawbacks such as slow response speed, oscillation around the MPP in steady state, and even tracking in wrong way under rapidly changing atmospheric conditions. In this paper, it is shown that the negative effects associated to such a drawback can be greatly reduced if the Artificial Intelligence (AI) concepts are used to improve P&O algorithm. The perturbation step is continuously approximated by using artificial neural network (ANN). By the simulation, the validity of the proposed control algorithm is proved.