The potential of novel data mining models for global solar radiation prediction
Advance knowledge of solar radiation is highly essential for multiple energy devotions such as sustainability in energy production and development of solar energy system. The current research investigates the capability of four data mining computation models, namely random forest (RF), random tree,...
Saved in:
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Published: |
Center for Environmental and Energy Research and Studies
2019
|
Subjects: | |
Online Access: | http://eprints.utm.my/id/eprint/88525/ http://dx.doi.org/10.1007/s13762-019-02344-0 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.utm.88525 |
---|---|
record_format |
eprints |
spelling |
my.utm.885252020-12-15T00:19:42Z http://eprints.utm.my/id/eprint/88525/ The potential of novel data mining models for global solar radiation prediction Sharafati, Ahmad Khosravi, Khabat Khosravinia, Payam Ahmed, Kamal Salman, Saleem Abdulridha Yaseen, Zaher Mundher Shahid, Shamsuddin TA Engineering (General). Civil engineering (General) Advance knowledge of solar radiation is highly essential for multiple energy devotions such as sustainability in energy production and development of solar energy system. The current research investigates the capability of four data mining computation models, namely random forest (RF), random tree, reduced error pruning trees and hybrid model of random committee with random tree reduce (RC) for predicting daily measured solar radiation at four locations of Burkina Faso, i.e., Bur Dedougou, Bobo-Dioulasso, Fada-Ngourma and Ouahigouya. Daily data of seven climatic variables, namely maximum and minimum air temperature, maximum and minimum relative humidity, wind speed, evaporation and vapor pressure deficit, for the period 1998–2012 are used for solar radiation prediction. Different combinations of input variables are used according to correlation coefficient between the predictors and predictand, and the best input combination is selected based on the sensitivity of model output measured in terms of statistical indices. The obtained results are found consistence for all the meteorological stations. The highest accuracy in prediction is found when all the climate variables are used as input. The RC and RF showed the minimal absolute error in prediction at all the stations. The RMSE and NSE are found in the range of 0.03–0.05 and 0.77–0.91 for RC and 0.03–0.05 and 0.78–0.92 for RF at different stations. The results indicate that the proposed data mining models can be used for accurate prediction of solar radiation over the Burkina Faso. Center for Environmental and Energy Research and Studies 2019 Article PeerReviewed Sharafati, Ahmad and Khosravi, Khabat and Khosravinia, Payam and Ahmed, Kamal and Salman, Saleem Abdulridha and Yaseen, Zaher Mundher and Shahid, Shamsuddin (2019) The potential of novel data mining models for global solar radiation prediction. International Journal of Environmental Science and Technology, 16 (11). pp. 7147-7164. ISSN 1735-1472 http://dx.doi.org/10.1007/s13762-019-02344-0 |
institution |
Universiti Teknologi Malaysia |
building |
UTM Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Teknologi Malaysia |
content_source |
UTM Institutional Repository |
url_provider |
http://eprints.utm.my/ |
topic |
TA Engineering (General). Civil engineering (General) |
spellingShingle |
TA Engineering (General). Civil engineering (General) Sharafati, Ahmad Khosravi, Khabat Khosravinia, Payam Ahmed, Kamal Salman, Saleem Abdulridha Yaseen, Zaher Mundher Shahid, Shamsuddin The potential of novel data mining models for global solar radiation prediction |
description |
Advance knowledge of solar radiation is highly essential for multiple energy devotions such as sustainability in energy production and development of solar energy system. The current research investigates the capability of four data mining computation models, namely random forest (RF), random tree, reduced error pruning trees and hybrid model of random committee with random tree reduce (RC) for predicting daily measured solar radiation at four locations of Burkina Faso, i.e., Bur Dedougou, Bobo-Dioulasso, Fada-Ngourma and Ouahigouya. Daily data of seven climatic variables, namely maximum and minimum air temperature, maximum and minimum relative humidity, wind speed, evaporation and vapor pressure deficit, for the period 1998–2012 are used for solar radiation prediction. Different combinations of input variables are used according to correlation coefficient between the predictors and predictand, and the best input combination is selected based on the sensitivity of model output measured in terms of statistical indices. The obtained results are found consistence for all the meteorological stations. The highest accuracy in prediction is found when all the climate variables are used as input. The RC and RF showed the minimal absolute error in prediction at all the stations. The RMSE and NSE are found in the range of 0.03–0.05 and 0.77–0.91 for RC and 0.03–0.05 and 0.78–0.92 for RF at different stations. The results indicate that the proposed data mining models can be used for accurate prediction of solar radiation over the Burkina Faso. |
format |
Article |
author |
Sharafati, Ahmad Khosravi, Khabat Khosravinia, Payam Ahmed, Kamal Salman, Saleem Abdulridha Yaseen, Zaher Mundher Shahid, Shamsuddin |
author_facet |
Sharafati, Ahmad Khosravi, Khabat Khosravinia, Payam Ahmed, Kamal Salman, Saleem Abdulridha Yaseen, Zaher Mundher Shahid, Shamsuddin |
author_sort |
Sharafati, Ahmad |
title |
The potential of novel data mining models for global solar radiation prediction |
title_short |
The potential of novel data mining models for global solar radiation prediction |
title_full |
The potential of novel data mining models for global solar radiation prediction |
title_fullStr |
The potential of novel data mining models for global solar radiation prediction |
title_full_unstemmed |
The potential of novel data mining models for global solar radiation prediction |
title_sort |
potential of novel data mining models for global solar radiation prediction |
publisher |
Center for Environmental and Energy Research and Studies |
publishDate |
2019 |
url |
http://eprints.utm.my/id/eprint/88525/ http://dx.doi.org/10.1007/s13762-019-02344-0 |
_version_ |
1687393583635628032 |
score |
13.18916 |