IC-based Variable Step Size Neuro-Fuzzy MPPT Improving PV System Performances

This paper addresses the development of a Neuro-Fuzzy IC variable step size MPPT controller. Firstly, the proposed MPPT controller is developed in an offline mode required for testing different set of neural network architectures and parameters, using the Fuzzy-based IC variable step size MPPT data. Secondly, the optimal found neural network controller is then used to track the output power of the PV system in an online mode. The inputs variables for the proposed neural network controller are same as for the Incremental Conductance algorithm inputs (i.e. I and V); while the output is the PWM ratio used to drive the DC-DC boost converter. The effectiveness of proposed Neuro-Fuzzy IC variable step size MPPT controller is investigated by implementing the model of the entire system using Matlab/Simulink environment, composed of Solarex MSX-60W PV panel operating at variable atmospheric conditions and DC-DC boost converter drived using the proposed controller. Simulation results prove that the proposed variable step size Neuro-Fuzzy IC MPPT outperforms the classical fixed step size IC MPPT in all considered performance measures which leads to the improvement of the output power and consequently the reduction of power losses. (C) 2018 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0/)