Dynamic neural control for maximum power point tracking of PV system

Abstract

Development of an effective maximum power point tracking (MPPT) algorithm is important in order to achieve maximum power point in a photovoltaic system (PV). In this study, a dynamic neural control (DNC) scheme is developed. The adaptation procedure is based on the back propagation learning law and is required only a priori knowledge, that's, the system output error. The feasibility of the proposed neural control is evaluated by the simulation results and compared to the conventional perturbation and observation (P&O) method.