A comparative study for Poly-Si Crystalline photovoltaic panel based on ANN modeling

Abstract

Photovoltaic (PV) cells are interconnected to form a PV panel which generates typically up to 50-200 Watts of power. This digest presented an artificial neural network (ANN) model of a PV panel that consists of Poly-Si crystalline solar cells. Panels that were modeled have been tested under the meteorological conditions in Istanbul, Turkey. Data relevant to the system performance was collected on December, 12th 2010 and every second during the half-day. This input-output data is used to train the ANN. An ANN has been developed for PV voltage from Poly-Si crystalline PV modules during any solar irradiance levels, panel back-surface temperatures, humidity, atmospheric pressure, and ambient temperature. The results show that the proposed ANN introduces a good accurate prediction for Poly-Si crystalline PV panels' performance when compared with the measured and model values. © Sila Science.