Estimation of Solar Radiation by Artificial Networks: East Coast Malaysia

Abstract

In this paper the solar radiation forecasting in Pekan located in Pahang is presented. The time series utilized are 10 minute solar radiation data obtained directly from the measurements realized in the sites during about one month. In order to do solar radiation forecasting, quick propagation algorithms Artificial Neural Network (ANN) models were developed. Around 1617 data's are taken to train ANN. The effects of temperature, humidity, wind speed, wind chill, pressure and rain on solar radiation are discussed in this paper. The maximum mean absolute percentage error was found to be less than 7.74% and R-squared (R2) values were found to be about 98.9% for the testing stations. However, these values were found to be 5.398% and 97.9 % for the training stations. The trained and tested ANN models show greater accuracy for evaluating the solar radiation. The predicted solar potential values from the ANN are given in the form of table where included the other variables such as temperature, humidity, wind speed, wind chill, pressure and rain. This table is of prime importance for different working disciplines, like scientists, architects, meteorologists and solar engineers, in Malaysia. The predictions from the ANN models could enable scientists to locate and design solar energy systems in Malaysia and determine the best solar technology

Analysis of variables to determine their influence on renewable energy forecasting using ensemble methods

“… Babar, Luppino, Boström & Anfinsen [ 19 ] Importance of sampling intervals The choice of sampling frequency significantly impacts the estimated amount of solar radiation. Fathima, Nedumpozhimana, Lee, Winkler & Dev [ 20 ]; Kadirgama, Amirruddin & Bakar [ 21 ]; Notton, Voyant, Fouilloy, Duchaud & Nivet [ 16 ]; Schuss, Eichberger & Rahkonen [ 22 ]; Reikard [ 23 ] Machine learning models for immediate rainfall forecasting Proposed models for immediate probabilistic rainfall forecasting at 10-min intervals for short lead times. Pirone, Cimorelli, Del Giudice & Pianés [ 24 ] Integrating photovoltaic performance model with machine learning Prediction of power output several hours in advance with a 5-min resolution.…”

Estimating the energy production of the wind turbine using artificial neural network

“…ANN widely accepted as a technique offering an alternative way to tackle complex problems in several engineering problems such as estimation of offshore bar volumes and seawater level, solar radiation forecasting, and prediction of meteorological parameters is a modeling and estimation tool [4][5][6][7]. On the other hand, many researchers have focused on the estimation of the wind power generation using various approaches in the last decade: Thiaw et al compared the Weibull and the ANN models applied to a time series consisting of ten years of wind speed observations in Dakar, Senegal.…”

Mathematical and neural network models for predicting the electrical performance of a PV/T system

“…Simulations attempt to describe and discuss the characteristics and the behavior of any physical system using a simulation system that emulates the functioning of the real system under artificial conditions. Many researchers used similar system modeling using artificial neural network (ANN); in Table , some of the most important of these studies are listed …”