arXiv：cs.AI· Josef Hoppe, Sarra Bouchkati, Farah Nasr, Jonathan Krapp, Alexander Och, Maximilian Wirth, Jan Schiefelbein-Lach, Oliver Pohl, Andreas Ulbig, Michael T. Schaub·· 13 小时前
基于强化学习的低压电网拥堵管理鲁棒性研究
Robustness of Reinforcement Learning-Based Congestion Management in Low-Voltage Grids
AI 导读
该研究将随机森林违规预分类器与 actor-critic 控制器解耦，在真实低压电网上评估其应对测量噪声与电网参数失配的鲁棒性。在电网参数准确时，控制器将总违规幅度降低 98.9%，且该性能在测试的测量噪声设置下几乎不变；电网模型失配更具挑战性，但在测试的失配假设下仍能缓解大部分违规。
正文
Abstract:Increases in photovoltaic generation, charging of electric vehicles and heat-pump demand challenge operating limits in low-voltage distribution grids. This requires curative curtailment methods that can operate under sparse observability, noisy measurements, and imperfect grid models. Unlike prior end-to-end reinforcement-learning approaches for partially observable curtailment, this work decouples congestion detection and control by combining a random-forest violation pre-classifier with an actor-critic controller, and evaluates its robustness to measurement noise and grid-parameter mismatch. The framework is tested on a real low-voltage grid using synthetic future operating scenarios with low observability and controllability. With accurate grid parameters, the controller reduces total violation magnitude by 98.9%, and this performance remains nearly unchanged under the tested measurement-noise settings. Grid-model mismatch proves to be more challenging, but the controller still mitigates most violations under the tested mismatch assumptions.
| Comments: | 6 pages, 5 figures. Published at SEST 2026 |
| Subjects: | Systems and Control (eess.SY); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2607.16004 [eess.SY] |
| (or arXiv:2607.16004v2 [eess.SY] for this version) | |
| https://doi.org/10.48550/arXiv.2607.16004 arXiv-issued DOI via DataCite |
|
| Journal reference: | J. Hoppe, S. Bouchkati, et al., "Robustness of Reinforcement Learning-Based Congestion Management in Low-Voltage Grids," 2026 International Conference on Smart Energy Systems and Technologies (SEST), Ciudad Real, Spain, 2026 |
| Related DOI: | https://doi.org/10.1109/SEST67798.2026.11712361
DOI(s) linking to related resources |
Submission history
From: Josef Hoppe [view email]
[v1]
Fri, 17 Jul 2026 14:39:48 UTC (614 KB)
[v2]
Fri, 9 Oct 2026 08:47:44 UTC (614 KB)
来源：arXiv：cs.AI · arxiv.org