Learning the Optimal Power Flow: Environment Design Matters
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909151198707712 |
|---|---|
| author | Wolgast, Thomas Nieße, Astrid |
| author_facet | Wolgast, Thomas Nieße, Astrid |
| contents | To solve the optimal power flow (OPF) problem, reinforcement learning (RL) emerges as a promising new approach. However, the RL-OPF literature is strongly divided regarding the exact formulation of the OPF problem as an RL environment. In this work, we collect and implement diverse environment design decisions from the literature regarding training data, observation space, episode definition, and reward function choice. In an experimental analysis, we show the significant impact of these environment design options on RL-OPF training performance. Further, we derive some first recommendations regarding the choice of these design decisions. The created environment framework is fully open-source and can serve as a benchmark for future research in the RL-OPF field. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_17831 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Learning the Optimal Power Flow: Environment Design Matters Wolgast, Thomas Nieße, Astrid Machine Learning Systems and Control To solve the optimal power flow (OPF) problem, reinforcement learning (RL) emerges as a promising new approach. However, the RL-OPF literature is strongly divided regarding the exact formulation of the OPF problem as an RL environment. In this work, we collect and implement diverse environment design decisions from the literature regarding training data, observation space, episode definition, and reward function choice. In an experimental analysis, we show the significant impact of these environment design options on RL-OPF training performance. Further, we derive some first recommendations regarding the choice of these design decisions. The created environment framework is fully open-source and can serve as a benchmark for future research in the RL-OPF field. |
| title | Learning the Optimal Power Flow: Environment Design Matters |
| topic | Machine Learning Systems and Control |
| url | https://arxiv.org/abs/2403.17831 |