Optimizing Operation of Photovoltaic System Using Neural Network and Fuzzy Logic

Authors: N. Drir, L. Barazane, M. Loudini

Abstract:

It is well known that photovoltaic (PV) cells are an attractive source of energy. Abundant and ubiquitous, this source is one of the important renewable energy sources that have been increasing worldwide year by year. However, in the V-P characteristic curve of GPV, there is a maximum point called the maximum power point (MPP) which depends closely on the variation of atmospheric conditions and the rotation of the earth. In fact, such characteristics outputs are nonlinear and change with variations of temperature and irradiation, so we need a controller named maximum power point tracker MPPT to extract the maximum power at the terminals of photovoltaic generator. In this context, the authors propose here to study the modeling of a photovoltaic system and to find an appropriate method for optimizing the operation of the PV generator using two intelligent controllers respectively to track this point. The first one is based on artificial neural networks and the second on fuzzy logic. After the conception and the integration of each controller in the global process, the performances are examined and compared through a series of simulation. These two controller have prove by their results good tracking of the MPPT compare with the other method which are proposed up to now.

Keywords: Maximum power point tracking, neural networks, photovoltaic, P&O.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1093368

References:

[1] S. Kaddah, Genetic Algorithm Based Optimal Operation for Photovoltaic Systems under Different Fault Criteria. The Eleventh International Middle East Power Systems Conference, (MEPCON'2006).
[2] P.S. Revankar, W.Z. Gandhare and A.G. Thosar, Maximum Power Point Tracking for PV Systems Using MATLAB/SIMULINK. In Proc Second Int. Conf. on Machine Learning and Computing (ICMLC), Bangalore, India, 2010, pp. 8-11
[3] T. Esram and P.L. Chapman, Comparison of photovoltaic array maximum power point tracking techniques. IEEE Transactions on Energy Conversion. 22(2), 2007, pp. 439-449.
[4] M. Angel Cid Pastor, Conception et réalisation de modules photovoltaïques électroniques, Thèse de doctorat, Institut National des Sciences Appliquées, Toulouse, France, 2006.
[5] F.S. Tymvios, C.P. Jacovides, S.C. Michaelides and C.Scouteli "Comparative study of Angstrom’s and artificial neural network’s methodologie in estimating global solar radiation”. Solar Energy, Vol. 78 n°6, 2005, pp.752-562.
[6] A. Panda, M. K. Pathak and S.P. Srivastava, "Fuzzy Intelligent Controller for The Maximum Power Point Tracking of a Photovoltaic Module at Varying Atmospheric Conditions". Journal of Energy Technologies and Policy, vol.1, no.2, pp. 18-27, 2011.
[7] S. Amamra, Commande par Réseaux de Neurones d’une Machine Asynchrone avec Linéarisation Hybride. Magister Memory, ENP, Alger, 2005. ” unpublished.
[8] A. Mellit, S.A. Kalogirou, L. Hontoria and S.Shaari "Artificial intelligence techniques for sizing photovoltaic systems’’ Renewable and sustainable Energy Reviews, Vol. 13 n°2, 2009, pp. 406-419.