A comparative study of artificial intelligent-based maximum power point tracking for photovoltaic systems

International Conference on Advances in Renewable Energy and Technologies 2016

Mutlag, Ammar Hussain^1,2 ; Mohamed, Azah^1 ; Shareef, Hussain^3

Department of Electrical, Electronic and Systems Engineering, Faculty of Engineering and Built Environment, Universiti Kebangsaan Malaysia, Bangi, Selangor

43600, Malaysia^1

College of Electrical and Electronic Engineering Techniques, Middle Technical University, Baghdad, Iraq^2

Department of Electrical Engineering, United Arab Emirates University, Al-Ain

15551, United Arab Emirates^3

关键词: Accurate performance;    Adaptive neuro-fuzzy inference system;    Artificial intelligent;    Artificial intelligent techniques;    Comparative studies;    Environmental conditions;    Maximum Power Point Tracking;    Photovoltaic systems;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/32/1/012014/pdf
DOI  :  10.1088/1755-1315/32/1/012014

来源: IOP

【 摘 要 】

Maximum power point tracking (MPPT) is normally required to improve the performance of photovoltaic (PV) systems. This paper presents artificial intelligent-based maximum power point tracking (AI-MPPT) by considering three artificial intelligent techniques, namely, artificial neural network (ANN), adaptive neuro fuzzy inference system with seven triangular fuzzy sets (7-tri), and adaptive neuro fuzzy inference system with seven gbell fuzzy sets. The AI-MPPT is designed for the 25 SolarTIFSTF-120P6 PV panels, with the capacity of 3 kW peak. A complete PV system is modelled using 300,000 data samples and simulated in the MATLAB/SIMULINK. The AI-MPPT has been tested under real environmental conditions for two days from 8 am to 18 pm. The results showed that the ANN based MPPT gives the most accurate performance and then followed by the 7-tri-based MPPT.