A Novel Adaptive Neural MPPT Algorithm for Photovoltaic System

  • S. A. Allahyari Mehriz Branch, Islamic Azad University, Mehriz, Iran
  • Nasser Taheri Electrical Engineering Department, Technical and Vocational University, Sabzevar, Iran
  • M. Zadehbagheri Yasouj Branch, Islamic Azad University, Kohgiloyeh & Bovirahmad Province, Yasouj, Iran
  • Z. Rahimkhani Sarvestan Branch, Islamic Azad University, Sarvestan, Iran
Keywords: Photovoltaic systems; adaptive neural networks; MPPT algorithm

Abstract

This paper presents a novel adaptive neural network (ANN) for maximum power point tracking (MPPT) in photovoltaic (PV) systems under variable working conditions. The ANN-based MPPT model includes two separate NNs for PV system identification and control. NNs are trained by using of a novel back propagation algorithm in pre/post control phases. Because of online optimal performance of NNs, the proposed method, not only overcome the common drawbacks of the conventional MPPT methods, but also gives a simple and a robust MPPT scheme. Simulation results, which carried on MATLAB, show that proposed controller is the most effective in comparison with conventional MPPT approaches.

Published
2018-10-05
How to Cite
Allahyari, S. A., Taheri, N., Zadehbagheri, M., & Rahimkhani, Z. (2018). A Novel Adaptive Neural MPPT Algorithm for Photovoltaic System. International Journal of Automotive and Mechanical Engineering, 15(3), 5421-5434. https://doi.org/10.15282/ijame.15.3.2018.2.0417