A Neural Network Based MPPT Technique Controller for Photovoltaic Pumping System

Mohammed Yaichi, Mohammed-Karim Fellah, Abdelkrim Mammeri


The article proposes a novel method using the artificial neural network (ANN) for the improvement of the performances of a photovoltaic system composed of a photovoltaic (PV) array, an inverter, a motor asynchronous and a centrifugal pump. For this type of system, different optimization strategies have been proposed to improve the over of the PV system efficiency, i.e. the PV generator is forced to operate at its maximum power point “MPPT”, generally, by the insertion of DC/DC boost converter between the photovoltaic array and the inverter. In this work we propose an approach, where optimization is realized without need adding a DC/DC converter to the chain, using field-oriented control through the monitoring of the voltage-fed inverter frequency. The motor is also ensured in all insolation conditions. A multilayer feed forward perception type NN is proposed for MPPT control, and the back-propagation algorithm is used for training. The performances of the drive with ANN-based MPPT are excellent. The maximum power point (MPP) can be easily obtained to frequency-controlled drive.

DOI: http://dx.doi.org/10.11591/ijpeds.v4i2.5875

Full Text:



  • There are currently no refbacks.

Copyright (c) 2014 Mohammed Yaichi, Mohammed-Karim Fellah, Abdelkrim Mammeri

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.