Ensemble Learning Approach for Probabilistic Forecasting of Solar Power Generation
Probabilistic forecasting accounts for the uncertainty in prediction that arises from inaccurate input data due to measurement errors, as well as the inherent inaccuracy of a prediction model. Because of the variable nature of renewable power generation depending on weather conditions, probabilistic...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2016-12-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1996-1073/9/12/1017 |
| _version_ | 1828390582154690560 |
|---|---|
| author | Azhar Ahmed Mohammed Zeyar Aung |
| author_facet | Azhar Ahmed Mohammed Zeyar Aung |
| author_sort | Azhar Ahmed Mohammed |
| collection | DOAJ |
| description | Probabilistic forecasting accounts for the uncertainty in prediction that arises from inaccurate input data due to measurement errors, as well as the inherent inaccuracy of a prediction model. Because of the variable nature of renewable power generation depending on weather conditions, probabilistic forecasting is well suited to it. For a grid-tied solar farm, it is increasingly important to forecast the solar power generation several hours ahead. In this study, we propose three different methods for ensemble probabilistic forecasting, derived from seven individual machine learning models, to generate 24-h ahead solar power forecasts. We have shown that while all of the individual machine learning models are more accurate than the traditional benchmark models, like autoregressive integrated moving average (ARIMA), the ensemble models offer even more accurate results than any individual machine learning model alone does. Furthermore, it is observed that running separate models on the data belonging to the same hour of the day vastly improves the accuracy of the results. Getting more accurate forecasts will help the stakeholders come up with better decisions in resource planning and control when large-scale solar farms are integrated into the power grid. |
| first_indexed | 2024-12-10T06:47:00Z |
| format | Article |
| id | doaj.art-e1507df4c35e40bf94311007edc01326 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-12-10T06:47:00Z |
| publishDate | 2016-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-e1507df4c35e40bf94311007edc013262022-12-22T01:58:38ZengMDPI AGEnergies1996-10732016-12-01912101710.3390/en9121017en9121017Ensemble Learning Approach for Probabilistic Forecasting of Solar Power GenerationAzhar Ahmed Mohammed0Zeyar Aung1Department of Electrical Engineering and Computer Science, Masdar Institute of Science and Technology, 54224 Abu Dhabi, UAEDepartment of Electrical Engineering and Computer Science, Masdar Institute of Science and Technology, 54224 Abu Dhabi, UAEProbabilistic forecasting accounts for the uncertainty in prediction that arises from inaccurate input data due to measurement errors, as well as the inherent inaccuracy of a prediction model. Because of the variable nature of renewable power generation depending on weather conditions, probabilistic forecasting is well suited to it. For a grid-tied solar farm, it is increasingly important to forecast the solar power generation several hours ahead. In this study, we propose three different methods for ensemble probabilistic forecasting, derived from seven individual machine learning models, to generate 24-h ahead solar power forecasts. We have shown that while all of the individual machine learning models are more accurate than the traditional benchmark models, like autoregressive integrated moving average (ARIMA), the ensemble models offer even more accurate results than any individual machine learning model alone does. Furthermore, it is observed that running separate models on the data belonging to the same hour of the day vastly improves the accuracy of the results. Getting more accurate forecasts will help the stakeholders come up with better decisions in resource planning and control when large-scale solar farms are integrated into the power grid.http://www.mdpi.com/1996-1073/9/12/1017solar powerprobabilistic forecastingregressionmachine learningensemble models |
| spellingShingle | Azhar Ahmed Mohammed Zeyar Aung Ensemble Learning Approach for Probabilistic Forecasting of Solar Power Generation Energies solar power probabilistic forecasting regression machine learning ensemble models |
| title | Ensemble Learning Approach for Probabilistic Forecasting of Solar Power Generation |
| title_full | Ensemble Learning Approach for Probabilistic Forecasting of Solar Power Generation |
| title_fullStr | Ensemble Learning Approach for Probabilistic Forecasting of Solar Power Generation |
| title_full_unstemmed | Ensemble Learning Approach for Probabilistic Forecasting of Solar Power Generation |
| title_short | Ensemble Learning Approach for Probabilistic Forecasting of Solar Power Generation |
| title_sort | ensemble learning approach for probabilistic forecasting of solar power generation |
| topic | solar power probabilistic forecasting regression machine learning ensemble models |
| url | http://www.mdpi.com/1996-1073/9/12/1017 |
| work_keys_str_mv | AT azharahmedmohammed ensemblelearningapproachforprobabilisticforecastingofsolarpowergeneration AT zeyaraung ensemblelearningapproachforprobabilisticforecastingofsolarpowergeneration |