Intelligent maximum power point tracking control for solar photovoltaic systems using fuzzy and neuro-fuzzy techniques

Abstract

A solar-photovoltaic (PV) system cannot optimize power transfer from the generator to the load due to the nonlinear characteristics of the PV arrays. Maximum power point tracking (MPPT) approaches are necessary to optimize the power output of PV arrays. This study introduces a dual intelligent MPPT framework using fuzzy-logic controller (FLC) and neuro-fuzzy controller (NFC) to enhance solar PV efficiency under dynamic environmental conditions. The FLC uses 49 fuzzy rules with seven membership functions (MFs) in a fuzzy interface system (FIS). The NFC is an extension of FLC and is constructed using the artificial neuro-fuzzy interface system (ANFIS). The work analyzes the simulation results and performance realization, including % power loss, system efficiency, and MPPT efficiency under variable irradiance and temperatures. The solar-PV system utilizes FLC and NFC to achieve MPPT efficiencies of 97.89% and 98.61%, respectively. Similarly, the solar-PV system employing FLC and NFC yields system efficiencies of 98.24% and 99.23% respectively. The proposed system using both FLC and NFC is compared with existing MPPT approaches, with better improvement in system efficiency.