提出新型物理信息图神经网络，显著提升中高压电网潮流计算精度与速度。
Physics-informed GNN for medium-high voltage AC power flow with edge-aware attention and line search correction operator
- 引入边感知注意力机制，显式编码线路物理特性，构建可微分算子层。
- 测试误差达0.00033 p.u.（电压）和0.08度（相角），精度比基线提升99.5%和87.1%。
- 支持流式小批量推理，较牛顿-拉夫逊法快2-5倍，适合实时场景应用。
物理信息图神经网络（PIGNN）已成为快速求解交流潮流问题的新方法，可替代传统牛顿-拉夫逊（NR）算法，尤其适用于需评估数千种场景的场合。然而，现有PIGNN在保持高速的同时仍需提升精度，尤其在推理阶段物理损失的软约束失效，限制了实际部署。本文提出PIGN-Attn-LS，结合边感知注意力机制，通过每条边的偏置显式编码线路物理特性，构建全可微分的已知算子层；同时引入基于回溯线搜索的全局校正算子，在推理时恢复有效的下降准则。训练与测试使用真实中/高压场景生成器，仅用NR生成参考状态。在4-32节点的保留高压电网测试中，该模型电压误差达0.00033 p.u.，相角误差为0.08度，分别优于基线PIGN-MLP 99.5%和87.1%。在4-1024节点电网上，流式小批量推理速度相较NR提升2-5倍。
原文摘要 · Abstract (English)
Physics-informed graph neural networks (PIGNNs) have emerged as fast AC power-flow solvers that can replace the classic NewtonRaphson (NR) solvers, especially when thousands of scenarios must be evaluated. However, current PIGNNs still need accuracy improvements at parity speed; in particular, the soft constraint on the physics loss is inoperative at inference, which can deter operational adoption. We address this with PIGNN-Attn-LS, combining an edge-aware attention mechanism that explicitly encodes line physics via per-edge biases to form a fully differentiable knownoperator layer inside the computation graph, with a backtracking line-search-based globalized correction operator that restores an operative decrease criterion at inference. Training and testing use a realistic High-/Medium-Voltage scenario generator, with NR used only to construct reference states. On held-out HV cases consisting of 4-32-bus grids, PIGNN-Attn-LS achieves a test RMSE of 0.00033 p.u. in voltage and 0.08 deg in angle, outperforming the PIGNN-MLP baseline by 99.5% and 87.1%, respectively. With streaming micro-batches, it delivers 2-5x faster batched inference than NR on 4-1024-bus grids.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。