Learning a local trading strategy: deep reinforcement learning for grid-scale renewable energy integration
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917846271918080 |
|---|---|
| author | Ju, Caleb Crozier, Constance |
| author_facet | Ju, Caleb Crozier, Constance |
| contents | Variable renewable generation increases the challenge of balancing power supply and demand. Grid-scale batteries co-located with generation can help mitigate this misalignment. This paper explores the use of reinforcement learning (RL) for operating grid-scale batteries co-located with solar power. Our results show RL achieves an average of 61% (and up to 96%) of the approximate theoretical optimal (non-causal) operation, outperforming advanced control methods on average. Our findings suggest RL may be preferred when future signals are hard to predict. Moreover, RL has two significant advantages compared to simpler rules-based control: (1) that solar energy is more effectively shifted towards high demand periods, and (2) increased diversity of battery dispatch across different locations, reducing potential ramping issues caused by super-position of many similar actions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_15422 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Learning a local trading strategy: deep reinforcement learning for grid-scale renewable energy integration Ju, Caleb Crozier, Constance Machine Learning Artificial Intelligence Systems and Control Optimization and Control Variable renewable generation increases the challenge of balancing power supply and demand. Grid-scale batteries co-located with generation can help mitigate this misalignment. This paper explores the use of reinforcement learning (RL) for operating grid-scale batteries co-located with solar power. Our results show RL achieves an average of 61% (and up to 96%) of the approximate theoretical optimal (non-causal) operation, outperforming advanced control methods on average. Our findings suggest RL may be preferred when future signals are hard to predict. Moreover, RL has two significant advantages compared to simpler rules-based control: (1) that solar energy is more effectively shifted towards high demand periods, and (2) increased diversity of battery dispatch across different locations, reducing potential ramping issues caused by super-position of many similar actions. |
| title | Learning a local trading strategy: deep reinforcement learning for grid-scale renewable energy integration |
| topic | Machine Learning Artificial Intelligence Systems and Control Optimization and Control |
| url | https://arxiv.org/abs/2411.15422 |