ANN based prognostication of the PV panel output power under various environmental conditions

Abstract

The modules of the photovoltaic (PV) generation system convert solar energy into direct current (dc) electricity. Many complex factors, such as temperature and dust, influence PV arrays operation, making it difficult to ensure the optimal utilization of the solar energy. Achieving maximum power output under all possible system operation conditions is an important target. This paper proposes the possibility of developing a reliable relationship between the PV system power generation and efficiency, and various environmental factors such as solar irradiance, temperature, dust, and wind, using artificial neural network (ANN). The study is considering different prediction horizons to identify the influence of climate variability on power output and efficiency of the PV modules and to maximize the system usability. The proposed system does not require any physical definitions of the modules in order to predict power output under varying weather conditions. Experimental implementation is conducted to demonstrate the effectiveness of the proposed system.