Improving Solar Radiation Nowcasts by Blending Data-Driven, Satellite-Images-Based and All-Sky-Imagers-Based Models Using Machine Learning Techniques
Accurate solar radiation nowcasting models are critical for the integration of the increasing solar energy in power systems. This work explored the benefits obtained by the blending of four all-sky-imagers (ASI)-based models, two satellite-images-based models and a data-driven model. Two blending ap...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/9/2328 |
| _version_ | 1797601792827064320 |
|---|---|
| author | Miguel López-Cuesta Ricardo Aler-Mur Inés María Galván-León Francisco Javier Rodríguez-Benítez Antonio David Pozo-Vázquez |
| author_facet | Miguel López-Cuesta Ricardo Aler-Mur Inés María Galván-León Francisco Javier Rodríguez-Benítez Antonio David Pozo-Vázquez |
| author_sort | Miguel López-Cuesta |
| collection | DOAJ |
| description | Accurate solar radiation nowcasting models are critical for the integration of the increasing solar energy in power systems. This work explored the benefits obtained by the blending of four all-sky-imagers (ASI)-based models, two satellite-images-based models and a data-driven model. Two blending approaches (general and horizon) and two blending models (linear and random forest (RF)) were evaluated. The relative contribution of the different forecasting models in the blended-models-derived benefits was also explored. The study was conducted in Southern Spain; blending models provide one-minute resolution 90 min-ahead GHI and DNI forecasts. The results show that the general approach and the RF blending model present higher performance and provide enhanced forecasts. The improvement in rRMSE values obtained by model blending was up to 30% for GHI (40% for DNI), depending on the forecasting horizon. The greatest improvement was found at lead times between 15 and 30 min, and was negligible beyond 50 min. The results also show that blending models using only the data-driven model and the two satellite-images-based models (one using high resolution images and the other using low resolution images) perform similarly to blending models that used the ASI-based forecasts. Therefore, it was concluded that suitable model blending might prevent the use of expensive (and highly demanding, in terms of maintenance) ASI-based systems for point nowcasting. |
| first_indexed | 2024-03-11T04:07:42Z |
| format | Article |
| id | doaj.art-2b35a78e5a05408c9f945fe4194fd8c7 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T04:07:42Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-2b35a78e5a05408c9f945fe4194fd8c72023-11-17T23:38:39ZengMDPI AGRemote Sensing2072-42922023-04-01159232810.3390/rs15092328Improving Solar Radiation Nowcasts by Blending Data-Driven, Satellite-Images-Based and All-Sky-Imagers-Based Models Using Machine Learning TechniquesMiguel López-Cuesta0Ricardo Aler-Mur1Inés María Galván-León2Francisco Javier Rodríguez-Benítez3Antonio David Pozo-Vázquez4Andalusian Institute for Earth System Research IISTA-CEAMA, Department of Physics, University of Jaen, 23071 Jaen, SpainEVANNAI Research Group, Department of Computing Science, University Carlos III, 28911 Madrid, SpainEVANNAI Research Group, Department of Computing Science, University Carlos III, 28911 Madrid, SpainAndalusian Institute for Earth System Research IISTA-CEAMA, Department of Physics, University of Jaen, 23071 Jaen, SpainAndalusian Institute for Earth System Research IISTA-CEAMA, Department of Physics, University of Jaen, 23071 Jaen, SpainAccurate solar radiation nowcasting models are critical for the integration of the increasing solar energy in power systems. This work explored the benefits obtained by the blending of four all-sky-imagers (ASI)-based models, two satellite-images-based models and a data-driven model. Two blending approaches (general and horizon) and two blending models (linear and random forest (RF)) were evaluated. The relative contribution of the different forecasting models in the blended-models-derived benefits was also explored. The study was conducted in Southern Spain; blending models provide one-minute resolution 90 min-ahead GHI and DNI forecasts. The results show that the general approach and the RF blending model present higher performance and provide enhanced forecasts. The improvement in rRMSE values obtained by model blending was up to 30% for GHI (40% for DNI), depending on the forecasting horizon. The greatest improvement was found at lead times between 15 and 30 min, and was negligible beyond 50 min. The results also show that blending models using only the data-driven model and the two satellite-images-based models (one using high resolution images and the other using low resolution images) perform similarly to blending models that used the ASI-based forecasts. Therefore, it was concluded that suitable model blending might prevent the use of expensive (and highly demanding, in terms of maintenance) ASI-based systems for point nowcasting.https://www.mdpi.com/2072-4292/15/9/2328solar energysolar irradiance nowcastingmachine learning models blendingall sky imagers (ASI)MSG satellite images |
| spellingShingle | Miguel López-Cuesta Ricardo Aler-Mur Inés María Galván-León Francisco Javier Rodríguez-Benítez Antonio David Pozo-Vázquez Improving Solar Radiation Nowcasts by Blending Data-Driven, Satellite-Images-Based and All-Sky-Imagers-Based Models Using Machine Learning Techniques Remote Sensing solar energy solar irradiance nowcasting machine learning models blending all sky imagers (ASI) MSG satellite images |
| title | Improving Solar Radiation Nowcasts by Blending Data-Driven, Satellite-Images-Based and All-Sky-Imagers-Based Models Using Machine Learning Techniques |
| title_full | Improving Solar Radiation Nowcasts by Blending Data-Driven, Satellite-Images-Based and All-Sky-Imagers-Based Models Using Machine Learning Techniques |
| title_fullStr | Improving Solar Radiation Nowcasts by Blending Data-Driven, Satellite-Images-Based and All-Sky-Imagers-Based Models Using Machine Learning Techniques |
| title_full_unstemmed | Improving Solar Radiation Nowcasts by Blending Data-Driven, Satellite-Images-Based and All-Sky-Imagers-Based Models Using Machine Learning Techniques |
| title_short | Improving Solar Radiation Nowcasts by Blending Data-Driven, Satellite-Images-Based and All-Sky-Imagers-Based Models Using Machine Learning Techniques |
| title_sort | improving solar radiation nowcasts by blending data driven satellite images based and all sky imagers based models using machine learning techniques |
| topic | solar energy solar irradiance nowcasting machine learning models blending all sky imagers (ASI) MSG satellite images |
| url | https://www.mdpi.com/2072-4292/15/9/2328 |
| work_keys_str_mv | AT miguellopezcuesta improvingsolarradiationnowcastsbyblendingdatadrivensatelliteimagesbasedandallskyimagersbasedmodelsusingmachinelearningtechniques AT ricardoalermur improvingsolarradiationnowcastsbyblendingdatadrivensatelliteimagesbasedandallskyimagersbasedmodelsusingmachinelearningtechniques AT inesmariagalvanleon improvingsolarradiationnowcastsbyblendingdatadrivensatelliteimagesbasedandallskyimagersbasedmodelsusingmachinelearningtechniques AT franciscojavierrodriguezbenitez improvingsolarradiationnowcastsbyblendingdatadrivensatelliteimagesbasedandallskyimagersbasedmodelsusingmachinelearningtechniques AT antoniodavidpozovazquez improvingsolarradiationnowcastsbyblendingdatadrivensatelliteimagesbasedandallskyimagersbasedmodelsusingmachinelearningtechniques |