This work presents the design, modeling, and implementation of a neural network inverse\nmodel controller for tracking the maximum power point of a photovoltaic (PV) module. A nonlinear\nautoregressive network with exogenous inputs (NARX) was implemented in a serial-parallel\narchitecture. The PV module mathematical modeling was developed, a buck converter was designed\nto operate in the continuous conduction mode with a switching frequency of 20 KHz, and the\ndynamic neural controller was designed using the Neural Network Toolbox from Matlab/Simulink\n(MathWorks, Natick, MA, USA), and it was implemented on an open-hardware Arduino Mega board.\nTo obtain the reference signals for the NARX and determine the 65 W PV module behavior, a system\nmade of a 0.8WPV cell, a temperature sensor, a voltage sensor and a static neural network, was used.\nTo evaluate performance a comparison with the P&O traditional algorithm was done in terms of\nresponse time and oscillations around the operating point. Simulation results demonstrated the\nsuperiority of neural controller over the P&O. Implementation results showed that approximately the\nsame power is obtained with both controllers, but the P&O controller presents oscillations between\n7 W and 10W, in contrast to the inverse controller, which had oscillations between 1 W and 2 W.
Loading....