A Floating Photovoltaic Power Output Prediction by Using Adaptive Neuro-Fuzzy Inference System

Abstract

This project focuses on the prediction of power output by using computational methods and the development of an Adaptive Neuro-Fuzzy Inference System (ANFIS) configuration for floating solar photovoltaics.  This prediction is needed since the power output of the photovoltaic (PV) system will not be the same as the power rating stated on the PV module sheet. Prediction for power output involved two main parameters, ambient temperature (T_amb) and solar irradiance (G) of Tasik G3, Universiti Tun Hussein Onn Malaysia. To predict the power output of solar panels, de-rating factors such as dirt, aging and mismatched modules also must be considered to get an accurate prediction.  It will be more efficient to be able to estimate the daily power output with accuracy by using deep learning tools such as ANFIS.