An Improved Maximum Power Point Tracking Controller for PV Systems Using Artificial Neural Network

This paper presents an improved maximum power point tracking (MPPT) controller for PV systems. An Artificial Neural Network and the classical P&O algorithm were employed to achieve this objective. MATLAB models for a neural network, PV module, and the classical P&O algorithm are developed. However, the developed MPPT uses the ANN to predict the optimum voltage of the PV system in order to extract the maximum power point (MPP). The developed ANN has a feedback propagation configuration and it has four inputs which are solar radiation, ambient temperature, and the temperature coefficients of Isc and Voc of the modeled PV module. Meanwhile, the optimum voltage of the PV system is the output of the developed ANN. Based on the results; the response of the proposed MPPT controller is faster than the classical P&O algorithm. Moreover, the average tracking efficiency of the developed algorithm was 95.51% as compared to 85.99% of the classical P&O algorithm. Such developed controller increases the conversion efficiency of a PV system. Streszczenie. W artykule zaprezentowano ulepszony układ śledzenia maksymalnej mocy w systemie fotowoltaicznym. Zastosowano sieć neuronową i klasyczny algorytm P&O. Sieć neuronowa w sprzężeniu zwrotnym ma cztery wejścia: promieniowanie słoneczne, temperatura otoczenia i współczynniki temperaturowe ISC i Voc. Wyjściem jest optymalne napięcie systemu. (Ulepszona metoda śledzenia maksymalnej mocy systemu fotowoltaicznego z wykorzystaniem sieci neuronowej)