E01
Commande neuro-floue d’un hacheur MPPT
F.Belhachat1, C. Larbes2, L. Barazane3, S. Kharzi4
1
Ecole Nationale Polytechnique, Département D’électronique.
Laboratoire des dispositifs de communication et de conversion photovoltaïque.
10 Avenue Hassen Badi,BP.182,El-Harrach,Alger,Algérie.
2
Ecole Nationale Polytechnique, Département D’électronique.
Laboratoire des dispositifs de communication et de conversion photovoltaïque.
10 Avenue Hassen Badi,BP.182,El-Harrach,Alger,Algérie.
3
Université des Sciences et de Technologie Houari Boumediene (USTHB)
Faculté d’électronique et informatique
BP.32, El-Alia, Bab-Ezzouar 16111, Alger, Algérie.
4
Centre de Développement des Energies Renouvelables
Route de l’Observatoire. BP.62. Bouzaréah, 16340,Alger, Algérie
E-mails : faiza2b@yahoo.fr; larbes_cher @yahoo.fr; lbarazane@yahoo.fr; ksouhila@hotmail.com
Abstract —Maximum power point trackers (MPPT) play an important role in photovoltaic (PV) power systems because they maximize the power output from a
PV system for a given set of conditions, and therefore maximize the array efficiency. This paper presents a novel MPPT method based on Neuro-fuzzy networks.
The new method gives a good maximum power operation of any PV array under different conditions such as changing insolation and temperature.
This paper presents the design of a controller for
Maximum Power Point Tracking (MPPT) of a photovoltaic system. The proposed controller relies upon an Adaptive Neuro-Fuzzy Inference System
(ANFIS) which is designed as a combination of the concepts of Sugeno fuzzy model and neural network.
The controller employs the ANFIS of five layers with twenty five fuzzy rules. Simulations with practical parameters show that our proposed MPPT using ANFIS outperform the conventional MPPT controller terms of tracking speed and accuracy.
Key words: photovoltaic, maximum power point tracking, converter, neural-fuzzy, ANFIS, controller.
I.INTRODUCTION
Un générateur photovoltaïque peut