Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2404.01646 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916189077241856 |
|---|---|
| author | Bhavsar, Sujal Moffitt, Vera Zaychik Appleby, Justin |
| author_facet | Bhavsar, Sujal Moffitt, Vera Zaychik Appleby, Justin |
| contents | Stochastic battery bidding in real-time energy markets is a nuanced process, with its efficacy depending on the accuracy of forecasts and the representative scenarios chosen for optimization. In this paper, we introduce a pioneering methodology that amalgamates Transformer-based forecasting with weighted constrained Dynamic Time Warping (wcDTW) to refine scenario selection. Our approach harnesses the predictive capabilities of Transformers to foresee Energy prices, while wcDTW ensures the selection of pertinent historical scenarios by maintaining the coherence between multiple uncertain products. Through extensive simulations in the PJM market for July 2023, our method exhibited a 10% increase in revenue compared to the conventional method, highlighting its potential to revolutionize battery bidding strategies in real-time markets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_01646 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Transformer meets wcDTW to improve real-time battery bids: A new approach to scenario selection Bhavsar, Sujal Moffitt, Vera Zaychik Appleby, Justin Machine Learning Computers and Society Stochastic battery bidding in real-time energy markets is a nuanced process, with its efficacy depending on the accuracy of forecasts and the representative scenarios chosen for optimization. In this paper, we introduce a pioneering methodology that amalgamates Transformer-based forecasting with weighted constrained Dynamic Time Warping (wcDTW) to refine scenario selection. Our approach harnesses the predictive capabilities of Transformers to foresee Energy prices, while wcDTW ensures the selection of pertinent historical scenarios by maintaining the coherence between multiple uncertain products. Through extensive simulations in the PJM market for July 2023, our method exhibited a 10% increase in revenue compared to the conventional method, highlighting its potential to revolutionize battery bidding strategies in real-time markets. |
| title | Transformer meets wcDTW to improve real-time battery bids: A new approach to scenario selection |
| topic | Machine Learning Computers and Society |
| url | https://arxiv.org/abs/2404.01646 |