Global Solar Radiation Forecasting Based On Meteorological Data Using Artificial Neural Network

Research Article
Premalatha N
DOI: 
http://dx.doi.org/10.24327/ijrsr.2019.1007.3794
Subject: 
science
KeyWords: 
Global solar Radiation, Artificial Neural Network, Ambient temperature, Relative humidity, Gradient descent back propagation, Levenberg-Marquardt training algorithm.
Abstract: 

The main objective of this work is to predict average daily global solar radiation (GSR) without any measuring instruments , in future time domain for Madurai city, located in Tamilnadu (India) by using Standard multilayered feed-forward, back-propagation neural network with LevenbergMarquardt (LM) training algorithm and Gradient descent back propagation (GD) algorithm. In order to train and test the neural network, three different artificial neural network models are developed, based on daily average meteorological data like maximum ambient air temperature, minimum ambient air temperature and minimum relative humidity values for predicting global solar radiation. The measured data were randomly selected for training, validation and testing the neural network. The results from the three artificial neural network models shows that using the minimum air temperature and day of the year outperforms the other cases with absolute mean percentage error of 5.36% and mean square error of 0.006 when training was done by using LM back propagation learning algorithm. From the results it is very clear that neural network is well capable of estimating GSR from simple and available meteorological data. It is expected that the models developed for daily global solar radiation will be useful to the designers of energy-related systems as well as to those who need to estimate the daily variation of global solar radiation for the specific location in Tamilnadu (India).