Solar Power Prediction with an Hour-based Ensemble Machine Learning Method
I n recent years, the share of solar power in total energy production has gained a rapid increase. Therefore, prediction of solar power production has become increasingly important for energy regulations. In this study we proposed an ensemble method which gives competitive prediction performance for...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Hitit University
2020-03-01
|
| Series: | Hittite Journal of Science and Engineering |
| Subjects: | |
| Online Access: | https://dergipark.org.tr/tr/download/article-file/1506524 |
| _version_ | 1797662666502701056 |
|---|---|
| author | Seyda Ertekin |
| author_facet | Seyda Ertekin |
| author_sort | Seyda Ertekin |
| collection | DOAJ |
| description | I n recent years, the share of solar power in total energy production has gained a rapid increase. Therefore, prediction of solar power production has become increasingly important for energy regulations. In this study we proposed an ensemble method which gives competitive prediction performance for solar power production. This method firstly decomposes the nonlinear power production data into components with a multi-scale decomposition technique such as Empirical Mode Decomposition EMD . These components are then enriched with the explanatory exogenous feature set. Finally, each component is separately modeled by nonlinear machine learning methods and their results are aggregated as final prediction. We use two different training approaches such as Hour-based and Day-based, for predicting the power production at each hour in a day. Experimental results show that our ensemble method with Hour-based approach outperform the examined machine learning methods |
| first_indexed | 2024-03-11T19:03:38Z |
| format | Article |
| id | doaj.art-b1c385a69e3a47bcbadfc53b20e53564 |
| institution | Directory Open Access Journal |
| issn | 2148-4171 |
| language | English |
| last_indexed | 2024-03-11T19:03:38Z |
| publishDate | 2020-03-01 |
| publisher | Hitit University |
| record_format | Article |
| series | Hittite Journal of Science and Engineering |
| spelling | doaj.art-b1c385a69e3a47bcbadfc53b20e535642023-10-10T11:17:28ZengHitit UniversityHittite Journal of Science and Engineering2148-41712020-03-0171354010.17350/HJSE19030000169150Solar Power Prediction with an Hour-based Ensemble Machine Learning MethodSeyda Ertekin0Middle East Technical University, Department of Computer Engineering, Ankara, TurkeyI n recent years, the share of solar power in total energy production has gained a rapid increase. Therefore, prediction of solar power production has become increasingly important for energy regulations. In this study we proposed an ensemble method which gives competitive prediction performance for solar power production. This method firstly decomposes the nonlinear power production data into components with a multi-scale decomposition technique such as Empirical Mode Decomposition EMD . These components are then enriched with the explanatory exogenous feature set. Finally, each component is separately modeled by nonlinear machine learning methods and their results are aggregated as final prediction. We use two different training approaches such as Hour-based and Day-based, for predicting the power production at each hour in a day. Experimental results show that our ensemble method with Hour-based approach outperform the examined machine learning methodshttps://dergipark.org.tr/tr/download/article-file/1506524solar powertime series forecastingmachine learningensemble methodsempirical mode decomposition |
| spellingShingle | Seyda Ertekin Solar Power Prediction with an Hour-based Ensemble Machine Learning Method Hittite Journal of Science and Engineering solar power time series forecasting machine learning ensemble methods empirical mode decomposition |
| title | Solar Power Prediction with an Hour-based Ensemble Machine Learning Method |
| title_full | Solar Power Prediction with an Hour-based Ensemble Machine Learning Method |
| title_fullStr | Solar Power Prediction with an Hour-based Ensemble Machine Learning Method |
| title_full_unstemmed | Solar Power Prediction with an Hour-based Ensemble Machine Learning Method |
| title_short | Solar Power Prediction with an Hour-based Ensemble Machine Learning Method |
| title_sort | solar power prediction with an hour based ensemble machine learning method |
| topic | solar power time series forecasting machine learning ensemble methods empirical mode decomposition |
| url | https://dergipark.org.tr/tr/download/article-file/1506524 |
| work_keys_str_mv | AT seydaertekin solarpowerpredictionwithanhourbasedensemblemachinelearningmethod |