物理信息图神经网络算子从稀疏 PMU 估计电力系统动态状态

架构上，图注意力编码器处理量测数据，摇摆方程以硬约束方式嵌入网络，或以软约束配合可学习的修正项吸收建模误差。训练完全基于仿真量测，不需要状态标签；在多 PMU 场景下采用掩码训练——把一台 PMU 从输入中隐藏但保留在损失函数中。在四个输电系统上的仿真显示，它是不做逐场景优化、也不用状态标签的估计器中最准确的；在模型误差较大时，它在 118 母线系统上比硬约束的 moving-horizon 估计更快且更准。

在存在模型误差时，该算子以一小部分计算成本达到或超过基于优化的基准方法的表现；结果在只通过电压相量观测的详细发电机模型上依然成立。对做电网状态估计的工程师来说，无标签训练这条路线降低了实测数据标注成本。

Dynamic State Estimation from Sparse PMUs via Physics-Informed Graph Neural Operators

This paper proposes a physics-informed graph neural operator for power system dynamic state estimation. From a sparse, intermittent measurement window at a few generator buses, the operator estimates the rotor-angle and speed trajectories of all machines, unmeasured ones included, in one forward pass. A graph-attention encoder processes the measurements, and the swing equations are imposed as a hard constraint or as a soft one with a learned correction that absorbs model errors. It is trained on simulated measurements, without state labels. With several phasor measurement units, masked training hides one from the input but keeps it in the loss. On four transmission systems, simulations show that the operator is the most accurate estimator that neither optimizes per scenario nor uses state labels, except on the smallest system at large model errors, where tuned Kalman smoothers are better. Networks trained on simulated states are more accurate on the two smallest systems but not on the 118-bus system, where the operator is faster and more accurate than hard-constrained moving-horizon estimation. Under model errors, it matches or outperforms an optimization-based benchmark at a fraction of its cost. The results hold for a detailed machine model with exact parameters seen only through voltage phasors.

本条情报归属 AITOP「论文」核心追踪栏目。在跨区域产业观察坐标中，该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线，反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括：图神经网络、电力系统、PMU、动态状态估计，读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。

信源核验说明：本文原始线索采编自「arXiv cs.LG」（@Huy Hoang Le, Haoguang Wang, Christian Moya, Marcos Netto, Guang Lin），经 AITOP 多维评分管线结构化提炼。