Determining of Solar Power by Using Machine Learning Methods in a Specified Region
In this study, it is aimed to estimate the solar power according to the hourly meteorological data of the specified location measured between 2002 and 2006 by using different Machine Learning (ML) algorithms. Data Mining Processes (DMP) were used to select the most appropriate input variables from t...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Faculty of Mechanical Engineering in Slavonski Brod, Faculty of Electrical Engineering in Osijek, Faculty of Civil Engineering in Osijek
2021-01-01
|
| Series: | Tehnički Vjesnik |
| Subjects: | |
| Online Access: | https://hrcak.srce.hr/file/380186 |
| _version_ | 1797206919529627648 |
|---|---|
| author | A. Burak Guher Sakir Tasdemir Bulent Yaniktepe* |
| author_facet | A. Burak Guher Sakir Tasdemir Bulent Yaniktepe* |
| author_sort | A. Burak Guher |
| collection | DOAJ |
| description | In this study, it is aimed to estimate the solar power according to the hourly meteorological data of the specified location measured between 2002 and 2006 by using different Machine Learning (ML) algorithms. Data Mining Processes (DMP) were used to select the most appropriate input variables from these measured data. Data groups created using DMP were evaluated according to three different ML algorithms such as Artificial Neural Network (ANN), Support Vector Regression (SVR) and K-Nearest Neighbors (KNN). It can be concluded that DMP-ML based prediction models are more successful than models developed using all available data. The most successful model developed among these models estimated the hourly solar power potential with an accuracy of 97%. Also, different error measurement statistics were used to evaluate ML algorithms. According to Symmetric Mean Absolute Percentage Error, 6.12%, 7.22% and 12.72% values were found in the most successful prediction models developed using ANN, KNN and SVR, respectively. In addition, from the meteorological data used in this study the most effective data on solar power as a result of DMP were shown to be Temperature and Hourly Sunshine Duration. |
| first_indexed | 2024-04-24T09:14:40Z |
| format | Article |
| id | doaj.art-42f9cdae7c1b44b0a93ed6163572593e |
| institution | Directory Open Access Journal |
| issn | 1330-3651 1848-6339 |
| language | English |
| last_indexed | 2024-04-24T09:14:40Z |
| publishDate | 2021-01-01 |
| publisher | Faculty of Mechanical Engineering in Slavonski Brod, Faculty of Electrical Engineering in Osijek, Faculty of Civil Engineering in Osijek |
| record_format | Article |
| series | Tehnički Vjesnik |
| spelling | doaj.art-42f9cdae7c1b44b0a93ed6163572593e2024-04-15T17:09:00ZengFaculty of Mechanical Engineering in Slavonski Brod, Faculty of Electrical Engineering in Osijek, Faculty of Civil Engineering in OsijekTehnički Vjesnik1330-36511848-63392021-01-012851471147910.17559/TV-20200425151543Determining of Solar Power by Using Machine Learning Methods in a Specified RegionA. Burak Guher0Sakir Tasdemir1Bulent Yaniktepe*2OsmaniyeKorkut Ata University, Osmaniye Vocational School, Karacaoglan Campus, 80000, Osmaniye, TurkeySelcuk University, Technology Faculty, Computer Engineering, Alaaddin Keykubat Campus, Selcuklu, 42075, Konya, TurkeyOsmaniye Korkut Ata University, Engineering Faculty, Energy Systems Eng. Dept., Karacaoglan Campus, 80000, Osmaniye, TurkeyIn this study, it is aimed to estimate the solar power according to the hourly meteorological data of the specified location measured between 2002 and 2006 by using different Machine Learning (ML) algorithms. Data Mining Processes (DMP) were used to select the most appropriate input variables from these measured data. Data groups created using DMP were evaluated according to three different ML algorithms such as Artificial Neural Network (ANN), Support Vector Regression (SVR) and K-Nearest Neighbors (KNN). It can be concluded that DMP-ML based prediction models are more successful than models developed using all available data. The most successful model developed among these models estimated the hourly solar power potential with an accuracy of 97%. Also, different error measurement statistics were used to evaluate ML algorithms. According to Symmetric Mean Absolute Percentage Error, 6.12%, 7.22% and 12.72% values were found in the most successful prediction models developed using ANN, KNN and SVR, respectively. In addition, from the meteorological data used in this study the most effective data on solar power as a result of DMP were shown to be Temperature and Hourly Sunshine Duration.https://hrcak.srce.hr/file/380186data mining processesmachine learningoptimal data analysissolar power |
| spellingShingle | A. Burak Guher Sakir Tasdemir Bulent Yaniktepe* Determining of Solar Power by Using Machine Learning Methods in a Specified Region Tehnički Vjesnik data mining processes machine learning optimal data analysis solar power |
| title | Determining of Solar Power by Using Machine Learning Methods in a Specified Region |
| title_full | Determining of Solar Power by Using Machine Learning Methods in a Specified Region |
| title_fullStr | Determining of Solar Power by Using Machine Learning Methods in a Specified Region |
| title_full_unstemmed | Determining of Solar Power by Using Machine Learning Methods in a Specified Region |
| title_short | Determining of Solar Power by Using Machine Learning Methods in a Specified Region |
| title_sort | determining of solar power by using machine learning methods in a specified region |
| topic | data mining processes machine learning optimal data analysis solar power |
| url | https://hrcak.srce.hr/file/380186 |
| work_keys_str_mv | AT aburakguher determiningofsolarpowerbyusingmachinelearningmethodsinaspecifiedregion AT sakirtasdemir determiningofsolarpowerbyusingmachinelearningmethodsinaspecifiedregion AT bulentyaniktepe determiningofsolarpowerbyusingmachinelearningmethodsinaspecifiedregion |