Photovoltaic Performance Using Modify Back Propagation Neural Network Based On 3 Different Solar Panels

Abstract

Depletion of natural resources and increasing demand of power, sustainable energy sources such as photovoltaics (PV) are becoming increasingly more reliable and important. However, the production PV output power is unable to meet in terms of supply and demand due to irregular of solar irradiance and temperature daily. Therefore, a proper method/tool of prediction is very crucial to manage photovoltaic performance system and optimize the corresponding energy management system. In this paper, the modified Back Propagation Neural Network (BPNN) architecture is investigated. The investigating was conducted to provide more accurate prediction and error for short-term period prediction. The networkcompromises of 2 inputs parameter; the module temperature and solar irradiance and 1 output parameter; AC Power. Early research was conducted based on forecast time period on May 2021 starting from 7am to 8pm (14 hour) daily from 3 different panels; monocrystalline, polycrystalline and thin film, which are located on the rooftop of PEARL lab building. The result obtained shows that polycrystalline panel performed the best compare to monocrystalline and thin film panels.