Advances in solar forecasting: Computer vision with deep learning
Renewable energy forecasting is crucial for integrating variable energy sources into the grid. It allows power systems to address the intermittency of the energy supply at different spatiotemporal scales. To anticipate the future impact of cloud displacements on the energy generated by solar facilit...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-09-01
|
| Series: | Advances in Applied Energy |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S266679242300029X |
| _version_ | 1797727619668508672 |
|---|---|
| author | Quentin Paletta Guillermo Terrén-Serrano Yuhao Nie Binghui Li Jacob Bieker Wenqi Zhang Laurent Dubus Soumyabrata Dev Cong Feng |
| author_facet | Quentin Paletta Guillermo Terrén-Serrano Yuhao Nie Binghui Li Jacob Bieker Wenqi Zhang Laurent Dubus Soumyabrata Dev Cong Feng |
| author_sort | Quentin Paletta |
| collection | DOAJ |
| description | Renewable energy forecasting is crucial for integrating variable energy sources into the grid. It allows power systems to address the intermittency of the energy supply at different spatiotemporal scales. To anticipate the future impact of cloud displacements on the energy generated by solar facilities, conventional modeling methods rely on numerical weather prediction or physical models, which have difficulties in assimilating cloud information and learning systematic biases. Augmenting computer vision with machine learning overcomes some of these limitations by fusing real-time cloud cover observations with surface measurements acquired from multiple sources. This Review summarizes recent progress in solar forecasting from multisensor Earth observations with a focus on deep learning, which provides the necessary theoretical framework to develop architectures capable of extracting relevant information from data generated by ground-level sky cameras, satellites, weather stations, and sensor networks. Overall, machine learning has the potential to significantly improve the accuracy and robustness of solar energy meteorology; however, more research is necessary to realize this potential and address its limitations. |
| first_indexed | 2024-03-12T11:02:13Z |
| format | Article |
| id | doaj.art-2a0e4232abc1496f94c7c1eae607001b |
| institution | Directory Open Access Journal |
| issn | 2666-7924 |
| language | English |
| last_indexed | 2024-03-12T11:02:13Z |
| publishDate | 2023-09-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Advances in Applied Energy |
| spelling | doaj.art-2a0e4232abc1496f94c7c1eae607001b2023-09-02T04:32:32ZengElsevierAdvances in Applied Energy2666-79242023-09-0111100150Advances in solar forecasting: Computer vision with deep learningQuentin Paletta0Guillermo Terrén-Serrano1Yuhao Nie2Binghui Li3Jacob Bieker4Wenqi Zhang5Laurent Dubus6Soumyabrata Dev7Cong Feng8Department of Engineering, University of Cambridge, UK; European Space Research Institute, European Space Agency, Italy; European Centre for Space Applications and Telecommunications, European Space Agency, UK; ENGIE Lab CRIGEN, France; Corresponding author at: ϕ-Lab, European Space Research Institute, European Space Agency, Italy.Environmental Studies Department, University of California Santa Barbara, USA; Environmental Markets Lab (emLab), University of California Santa Barbara, USADepartment of Energy Science and Engineering, Stanford University, USAPower & Energy Systems, Idaho National Laboratory, USAOpen Climate Fix, UKGrid Planning & Analysis Center, National Renewable Energy Laboratory, USARéseau de Transport d'Électricité, France; World Energy & Meteorology Council, UKSchool of Computer Science, University College Dublin, IrelandPower Systems Engineering Center, National Renewable Energy Laboratory, USA; Corresponding author at: Power Systems Engineering Center, National Renewable Energy Laboratory, USA.Renewable energy forecasting is crucial for integrating variable energy sources into the grid. It allows power systems to address the intermittency of the energy supply at different spatiotemporal scales. To anticipate the future impact of cloud displacements on the energy generated by solar facilities, conventional modeling methods rely on numerical weather prediction or physical models, which have difficulties in assimilating cloud information and learning systematic biases. Augmenting computer vision with machine learning overcomes some of these limitations by fusing real-time cloud cover observations with surface measurements acquired from multiple sources. This Review summarizes recent progress in solar forecasting from multisensor Earth observations with a focus on deep learning, which provides the necessary theoretical framework to develop architectures capable of extracting relevant information from data generated by ground-level sky cameras, satellites, weather stations, and sensor networks. Overall, machine learning has the potential to significantly improve the accuracy and robustness of solar energy meteorology; however, more research is necessary to realize this potential and address its limitations.http://www.sciencedirect.com/science/article/pii/S266679242300029XSolar forecastingComputer visionDeep learningSatellite imagerySky imagesSolar irradiance |
| spellingShingle | Quentin Paletta Guillermo Terrén-Serrano Yuhao Nie Binghui Li Jacob Bieker Wenqi Zhang Laurent Dubus Soumyabrata Dev Cong Feng Advances in solar forecasting: Computer vision with deep learning Advances in Applied Energy Solar forecasting Computer vision Deep learning Satellite imagery Sky images Solar irradiance |
| title | Advances in solar forecasting: Computer vision with deep learning |
| title_full | Advances in solar forecasting: Computer vision with deep learning |
| title_fullStr | Advances in solar forecasting: Computer vision with deep learning |
| title_full_unstemmed | Advances in solar forecasting: Computer vision with deep learning |
| title_short | Advances in solar forecasting: Computer vision with deep learning |
| title_sort | advances in solar forecasting computer vision with deep learning |
| topic | Solar forecasting Computer vision Deep learning Satellite imagery Sky images Solar irradiance |
| url | http://www.sciencedirect.com/science/article/pii/S266679242300029X |
| work_keys_str_mv | AT quentinpaletta advancesinsolarforecastingcomputervisionwithdeeplearning AT guillermoterrenserrano advancesinsolarforecastingcomputervisionwithdeeplearning AT yuhaonie advancesinsolarforecastingcomputervisionwithdeeplearning AT binghuili advancesinsolarforecastingcomputervisionwithdeeplearning AT jacobbieker advancesinsolarforecastingcomputervisionwithdeeplearning AT wenqizhang advancesinsolarforecastingcomputervisionwithdeeplearning AT laurentdubus advancesinsolarforecastingcomputervisionwithdeeplearning AT soumyabratadev advancesinsolarforecastingcomputervisionwithdeeplearning AT congfeng advancesinsolarforecastingcomputervisionwithdeeplearning |