ARTIFICIAL NEURAL NETWORK-BASED PHOTOVOLTAIC MAXIMUM POWER POINT TRACKING
Abstract
This paper proposes an artificial neural network-based photovoltaic maximum power point tracking (MPPT) system to improve the energy efficiency of photovoltaic (PV) systems. The proposed system consists of a neural network model, which is trained with the input-output data of the PV system to predict the maximum power point (MPP) of the PV module. The neural network model is trained using the Levenberg-Marquardt algorithm, and the inputs to the model are the PV voltage and current. The output of the model is the MPP voltage and current, which are used to adjust the duty cycle of the boost converter to extract maximum power from the PV module. The proposed system is simulated in MATLAB/Simulink and compared with conventional perturb-and-observe (P&O) and incremental conductance (INC) MPPT algorithms. The simulation results show that the proposed system provides faster and more accurate MPP tracking, improved energy efficiency, and reduced oscillations around the MPP, making it a promising MPPT technique for PV systems.
Keywords
Maximum Power Point, Buck-Boost Converter, Neural Network Architecture.