Forecasting Solar Power Generation Using Fuzzy Logic and Artificial Neural Network

Abstract

This paper presents the study done on forecasting solar photovoltaic (PV) plant output power using fuzzy logic and artificial neural network methods. Fuzzy logic aided by high performance computer processors enables acceptable accuracy predictions of solar plants outputs and enables system flexibility to consider natural circumstances. Artificial neural network (ANN) technique has capabilities of machine learning and pattern recognition; and is widely used for forecasting purposes. The main objective of the study presented in this paper is to conduct production forecasting of a solar PV plant which will be useful in effective load management and in studying the reliability of the system supplying electrical power to a distribution network. The fuzzy logic method used to mimic the solar PV plant was successfully developed as the average percentage error obtained is 1.9 %. Similarly for ANN method the obtained average error was 2.6 %. The study has been conducted using MATLAB.