Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2502.10307 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908637031563264 |
|---|---|
| author | Mishra, Aditya T, Ravindra Iyengar, Srinivasan Kalyanaraman, Shivkumar Kumaraguru, Ponnurangam |
| author_facet | Mishra, Aditya T, Ravindra Iyengar, Srinivasan Kalyanaraman, Shivkumar Kumaraguru, Ponnurangam |
| contents | Traditional solar forecasting models are based on several years of site-specific historical irradiance data, often spanning five or more years, which are unavailable for newer photovoltaic farms. As renewable energy is highly intermittent, building accurate solar irradiance forecasting systems is essential for efficient grid management and enabling the ongoing proliferation of solar energy, which is crucial to achieve the United Nations' net zero goals. In this work, we propose SPIRIT, a novel approach leveraging foundation models for solar irradiance forecasting, making it applicable to newer solar installations. Our approach outperforms state-of-the-art models in zero-shot transfer learning by about 70%, enabling effective performance at new locations without relying on any historical data. Further improvements in performance are achieved through fine-tuning, as more location-specific data becomes available. These findings are supported by statistical significance, further validating our approach. SPIRIT represents a pivotal step towards rapid, scalable, and adaptable solar forecasting solutions, advancing the integration of renewable energy into global power systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_10307 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SPIRIT: Short-term Prediction of solar IRradIance for zero-shot Transfer learning using Foundation Models Mishra, Aditya T, Ravindra Iyengar, Srinivasan Kalyanaraman, Shivkumar Kumaraguru, Ponnurangam Machine Learning Computer Vision and Pattern Recognition Traditional solar forecasting models are based on several years of site-specific historical irradiance data, often spanning five or more years, which are unavailable for newer photovoltaic farms. As renewable energy is highly intermittent, building accurate solar irradiance forecasting systems is essential for efficient grid management and enabling the ongoing proliferation of solar energy, which is crucial to achieve the United Nations' net zero goals. In this work, we propose SPIRIT, a novel approach leveraging foundation models for solar irradiance forecasting, making it applicable to newer solar installations. Our approach outperforms state-of-the-art models in zero-shot transfer learning by about 70%, enabling effective performance at new locations without relying on any historical data. Further improvements in performance are achieved through fine-tuning, as more location-specific data becomes available. These findings are supported by statistical significance, further validating our approach. SPIRIT represents a pivotal step towards rapid, scalable, and adaptable solar forecasting solutions, advancing the integration of renewable energy into global power systems. |
| title | SPIRIT: Short-term Prediction of solar IRradIance for zero-shot Transfer learning using Foundation Models |
| topic | Machine Learning Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.10307 |