← 研踪 PaperTrailarXiv:2604.01830 · v2
Physics Informed Reinforcement Learning with Gibbs Priors for Topology Control in Power Grids
首次提交 2026-04-02 17:45
版本更新 2026-11-17 06:28
雷达观测 2026-11-18 19:43
摘要
Topology control for power grid operation is a challenging sequential decision making problem because the action space grows combinatorially with the size of the grid and action evaluation through simulation is computationally expensive. We propose a physics-informed Reinforcement Learning framework that combines semi-Markov control with a Gibbs prior, that encodes the system's physics, over the action space. The decision is only taken when the grid enters a hazardous regime, while a graph neural network surrogate predicts the post action overload risk of feasible topology actions. These predictions are used to construct a physics-informed Gibbs prior that both selects a small state-dependent candidate set and reweights policy logits before action selection. In this way, our method reduces exploration difficulty and online simulation cost while preserving the flexibility of a learned policy. We evaluate the approach in three realistic benchmark environments of increasing difficulty. Across all settings, the proposed method achieves a strong balance between control quality and computational efficiency: it matches oracle-level performance while being approximately faster on the first benchmark, reaches of oracle reward with roughly lower decision time on the second one, and on the most challenging benchmark improves over a PPO baseline by up to in reward and in survived steps while remaining about faster than a strong specialized engineering baseline. These results show that our method provides an effective mechanism for topology control in power grids.
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v2 · 2026-11-17 06:28 · 最新观测版本
Physics Informed Reinforcement Learning with Gibbs Priors for Topology Control in Power Grids
Topology control for power grid operation is a challenging sequential decision making problem because the action space grows combinatorially with the size of the grid and action evaluation through simulation is computationally expensive. We propose a physics-informed Reinforcement Learning framework that combines semi-Markov control with a Gibbs prior, that encodes the system's physics, over the action space. The decision is only taken when the grid enters a hazardous regime, while a graph neural network surrogate predicts the post action overload risk of feasible topology actions. These predictions are used to construct a physics-informed Gibbs prior that both selects a small state-dependent candidate set and reweights policy logits before action selection. In this way, our method reduces exploration difficulty and online simulation cost while preserving the flexibility of a learned policy. We evaluate the approach in three realistic benchmark environments of increasing difficulty. Across all settings, the proposed method achieves a strong balance between control quality and computational efficiency: it matches oracle-level performance while being approximately faster on the first benchmark, reaches of oracle reward with roughly lower decision time on the second one, and on the most challenging benchmark improves over a PPO baseline by up to in reward and in survived steps while remaining about faster than a strong specialized engineering baseline. These results show that our method provides an effective mechanism for topology control in power grids.
查看此版本解读 →查看此版本原文 ↗