Deep Reinforcement Learning for Power Grid Multi-Stage Cascading Failure Mitigation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918020036689920 |
|---|---|
| author | Meng, Bo Xu, Chenghao Zhu, Yongli |
| author_facet | Meng, Bo Xu, Chenghao Zhu, Yongli |
| contents | Cascading failures in power grids can lead to grid collapse, causing severe disruptions to social operations and economic activities. In certain cases, multi-stage cascading failures can occur. However, existing cascading-failure-mitigation strategies are usually single-stage-based, overlooking the complexity of the multi-stage scenario. This paper treats the multi-stage cascading failure problem as a reinforcement learning task and develops a simulation environment. The reinforcement learning agent is then trained via the deterministic policy gradient algorithm to achieve continuous actions. Finally, the effectiveness of the proposed approach is validated on the IEEE 14-bus and IEEE 118-bus systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_09012 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Deep Reinforcement Learning for Power Grid Multi-Stage Cascading Failure Mitigation Meng, Bo Xu, Chenghao Zhu, Yongli Artificial Intelligence Systems and Control Cascading failures in power grids can lead to grid collapse, causing severe disruptions to social operations and economic activities. In certain cases, multi-stage cascading failures can occur. However, existing cascading-failure-mitigation strategies are usually single-stage-based, overlooking the complexity of the multi-stage scenario. This paper treats the multi-stage cascading failure problem as a reinforcement learning task and develops a simulation environment. The reinforcement learning agent is then trained via the deterministic policy gradient algorithm to achieve continuous actions. Finally, the effectiveness of the proposed approach is validated on the IEEE 14-bus and IEEE 118-bus systems. |
| title | Deep Reinforcement Learning for Power Grid Multi-Stage Cascading Failure Mitigation |
| topic | Artificial Intelligence Systems and Control |
| url | https://arxiv.org/abs/2505.09012 |