Modelling of Fuzzy Logic Controller of a Maximum Power Point Tracker Based on Artificial Neural Network

The Grid Connected Photovoltaic System (GCPV) has become more used system in renewable energy. Several researches have been carried out to improve the efficiency and the decrease of energy losses. One of the important components used to increase the efficiency is the DC/DC boost converter. In this paper, a new hybrid model is proposed to control the DC/DC converter, this new controller is built on the fuzzy logic controller (FLC) and artificial neural network (ANN). The pathway taken to build the model is divided into three steps, the first step is to generate a data based on the FLC, the next step is to choose an ANN structure for modeling the FLC and the last step is the test and the validation of the obtained model. The phase of building an ANN is achieved by supervised learning based on back-propagation algorithm. This algorithm is used to train the ANN model by searching of the optimal weights and thresholds that has been a minimal root mean square error between the FLC output and the ANN model. The validation test was performed with various irradiation values between the both intelligent controllers and classical P&O algorithm simultaneously.

I. Introduction

Nowadays, the renewable energy, especially the solar energy, has become an important source of electricity. Therefore, many kinds of systems were introduced to exploit this energy such as the grid connected and the stand-alone systems in which they are varying in their characteristics and applications. Because of its advantages such as the support of the public grid and the needless of the storage systems, the grid connected PV is currently the most growing system. Basically, this system is composed of PV array, the DC/DC converter, the DC/AC inverter and the network [1], where the PV field is the generator source. The power generated by the PV depends strongly to the metrological conditions like the ambient temperature and the solar irradiation; both are unpredictable and change randomly. On the other hand, the temperature and the irradiation are inputs of the PV system, whereas the power generated from PV system that consists of the current and the voltage (I-V) is considered as output of the system [2]–[3]. According to the load variation, the PV module is characterized by a nonlinear function, this function is known as I-V characteristic which has an optimum point that corresponds to the maximum of power with which the load should be adapted [4]–[6]. For this reason, a flexible dynamic load is introduced by using DC/DC converter that can be controlled by maximum power point tracking (MPPT) algorithm. Hence, several algorithms of MPPT have been developed in the literature to control the converter switch by varying the duty cycle of PWM signal [7]. The necessity of the MPPT consists of avoiding any loss of energy under the weather conditions variation.