Forecasting Daily Solar Radiation Using CEEMDAN Decomposition-Based MARS Model Trained by Crow Search Algorithm
The precise forecasting of daily solar radiation (DSR) is receiving prominent attention among thriving solar energy studies. In this study, three standalone models, including gene expression programing (GEP), multivariate adaptive regression splines (MARS), and self-adaptive MARS (SaMARS), were eval...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-04-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/12/8/1416 |
| _version_ | 1798035391346900992 |
|---|---|
| author | Mohammad Rezaie-Balf Niloofar Maleki Sungwon Kim Ali Ashrafian Fatemeh Babaie-Miri Nam Won Kim Il-Moon Chung Sina Alaghmand |
| author_facet | Mohammad Rezaie-Balf Niloofar Maleki Sungwon Kim Ali Ashrafian Fatemeh Babaie-Miri Nam Won Kim Il-Moon Chung Sina Alaghmand |
| author_sort | Mohammad Rezaie-Balf |
| collection | DOAJ |
| description | The precise forecasting of daily solar radiation (DSR) is receiving prominent attention among thriving solar energy studies. In this study, three standalone models, including gene expression programing (GEP), multivariate adaptive regression splines (MARS), and self-adaptive MARS (SaMARS), were evaluated to forecast DSR. A SaMARS model was classified as MARS model when using the crow search algorithm (CSA). In addition, to overcome the limitations of the standalone models, the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) was employed to enhance the accuracy of DSR forecasting. Therefore, three hybrid models including CEEMDAN-GEP, CEEMDAN-MARS, and CEEMDAN-SaMARS were proposed to forecast DSR in Busan and Incheon stations in South Korea. The performance of proposed models were evaluated and affirmed that the accuracy of the CEEMDAN-SaMARS model (NSE = 0.878–0.883) outperformed CEEMDAN-MARS (NSE = 0.819–0.818), CEEMDAN-GEP (NSE = 0.873–0.789), SaMARS (NSE = 0.846–0.769), MARS (NSE = 0.819–0.758), and GEP (NSE = 0.814–0.755) models at both stations. Therefore, it can be concluded that the optimized CEEMDAN-SaMARS model significantly enhanced the accuracy of DSR forecasting compared to that of standalone models. |
| first_indexed | 2024-04-11T20:57:26Z |
| format | Article |
| id | doaj.art-84f2f85bfd4246ff9267f63b1c849eb6 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-04-11T20:57:26Z |
| publishDate | 2019-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-84f2f85bfd4246ff9267f63b1c849eb62022-12-22T04:03:38ZengMDPI AGEnergies1996-10732019-04-01128141610.3390/en12081416en12081416Forecasting Daily Solar Radiation Using CEEMDAN Decomposition-Based MARS Model Trained by Crow Search AlgorithmMohammad Rezaie-Balf0Niloofar Maleki1Sungwon Kim2Ali Ashrafian3Fatemeh Babaie-Miri4Nam Won Kim5Il-Moon Chung6Sina Alaghmand7Department of Civil Engineering, Graduate University of Advanced Technology, Kerman 76318-18356, IranDepartment of Civil Engineering, Pardisan University, Freidoonkenar 74715-47516, IranDepartment of Railroad Construction and Safety Engineering, Dongyang University, Yeongju 36040, KoreaDepartment of Civil Engineering, Tabari University of Babol, Babol 47139-75689, IranDepartment of Physical Education, Shahid Bahonar University, Kerman 76169-13439, IranDepartment of Land, Water and Environment Research, Korea Institute of Civil Engineering and Building Technology, Goyang 10223, KoreaDepartment of Land, Water and Environment Research, Korea Institute of Civil Engineering and Building Technology, Goyang 10223, KoreaDepartment of Civil Engineering, Monash University, 23 College Walk, Clayton, VIC 3800, AustraliaThe precise forecasting of daily solar radiation (DSR) is receiving prominent attention among thriving solar energy studies. In this study, three standalone models, including gene expression programing (GEP), multivariate adaptive regression splines (MARS), and self-adaptive MARS (SaMARS), were evaluated to forecast DSR. A SaMARS model was classified as MARS model when using the crow search algorithm (CSA). In addition, to overcome the limitations of the standalone models, the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) was employed to enhance the accuracy of DSR forecasting. Therefore, three hybrid models including CEEMDAN-GEP, CEEMDAN-MARS, and CEEMDAN-SaMARS were proposed to forecast DSR in Busan and Incheon stations in South Korea. The performance of proposed models were evaluated and affirmed that the accuracy of the CEEMDAN-SaMARS model (NSE = 0.878–0.883) outperformed CEEMDAN-MARS (NSE = 0.819–0.818), CEEMDAN-GEP (NSE = 0.873–0.789), SaMARS (NSE = 0.846–0.769), MARS (NSE = 0.819–0.758), and GEP (NSE = 0.814–0.755) models at both stations. Therefore, it can be concluded that the optimized CEEMDAN-SaMARS model significantly enhanced the accuracy of DSR forecasting compared to that of standalone models.https://www.mdpi.com/1996-1073/12/8/1416solar radiation forecastingmultivariate adaptive regression splinescrow search algorithmcomplete ensemble empirical mode decomposition with adaptive noisegene expression programing |
| spellingShingle | Mohammad Rezaie-Balf Niloofar Maleki Sungwon Kim Ali Ashrafian Fatemeh Babaie-Miri Nam Won Kim Il-Moon Chung Sina Alaghmand Forecasting Daily Solar Radiation Using CEEMDAN Decomposition-Based MARS Model Trained by Crow Search Algorithm Energies solar radiation forecasting multivariate adaptive regression splines crow search algorithm complete ensemble empirical mode decomposition with adaptive noise gene expression programing |
| title | Forecasting Daily Solar Radiation Using CEEMDAN Decomposition-Based MARS Model Trained by Crow Search Algorithm |
| title_full | Forecasting Daily Solar Radiation Using CEEMDAN Decomposition-Based MARS Model Trained by Crow Search Algorithm |
| title_fullStr | Forecasting Daily Solar Radiation Using CEEMDAN Decomposition-Based MARS Model Trained by Crow Search Algorithm |
| title_full_unstemmed | Forecasting Daily Solar Radiation Using CEEMDAN Decomposition-Based MARS Model Trained by Crow Search Algorithm |
| title_short | Forecasting Daily Solar Radiation Using CEEMDAN Decomposition-Based MARS Model Trained by Crow Search Algorithm |
| title_sort | forecasting daily solar radiation using ceemdan decomposition based mars model trained by crow search algorithm |
| topic | solar radiation forecasting multivariate adaptive regression splines crow search algorithm complete ensemble empirical mode decomposition with adaptive noise gene expression programing |
| url | https://www.mdpi.com/1996-1073/12/8/1416 |
| work_keys_str_mv | AT mohammadrezaiebalf forecastingdailysolarradiationusingceemdandecompositionbasedmarsmodeltrainedbycrowsearchalgorithm AT niloofarmaleki forecastingdailysolarradiationusingceemdandecompositionbasedmarsmodeltrainedbycrowsearchalgorithm AT sungwonkim forecastingdailysolarradiationusingceemdandecompositionbasedmarsmodeltrainedbycrowsearchalgorithm AT aliashrafian forecastingdailysolarradiationusingceemdandecompositionbasedmarsmodeltrainedbycrowsearchalgorithm AT fatemehbabaiemiri forecastingdailysolarradiationusingceemdandecompositionbasedmarsmodeltrainedbycrowsearchalgorithm AT namwonkim forecastingdailysolarradiationusingceemdandecompositionbasedmarsmodeltrainedbycrowsearchalgorithm AT ilmoonchung forecastingdailysolarradiationusingceemdandecompositionbasedmarsmodeltrainedbycrowsearchalgorithm AT sinaalaghmand forecastingdailysolarradiationusingceemdandecompositionbasedmarsmodeltrainedbycrowsearchalgorithm |