用物理规律提升电网电压预测模型的泛化能力。
Physics-Informed Inductive Biases for Voltage Prediction in Distribution Grids
- 引入电力潮流约束损失、复数神经网络等物理先验知识
- 在ENGAGE数据集上显著提升外分布泛化性能
- 适合关注电网智能运维与可解释建模的研究者
配电系统中的电压预测对保障电力系统稳定至关重要，但极具挑战。机器学习方法（尤其是图神经网络）虽能大幅提升计算速度，但在数据有限或不完整时泛化能力差。本文系统研究了物理信息先验对模型学习功率流能力的改进作用，评估了三种策略：(i) 功率潮流约束损失函数，(ii) 复数域神经网络，(iii) 基于残差的任務重构。基于涵盖多个低压与中压配电网结构的ENGAGE数据集，通过受控实验分离各先验的影响，评估标准预测性能及分布外泛化能力。研究为现代配电网络中可靠高效的电压预测提供了实用指导。
原文摘要 · Abstract (English)
Voltage prediction in distribution grids is a critical yet difficult task for maintaining power system stability. Machine learning approaches, particularly Graph Neural Networks (GNNs), offer significant speedups but suffer from poor generalization when trained on limited or incomplete data. In this work, we systematically investigate the role of inductive biases in improving a model's ability to reliably learn power flow. Specifically, we evaluate three physics-informed strategies: (i) power-flow-constrained loss functions, (ii) complex-valued neural networks, and (iii) residual-based task reformulation. Using the ENGAGE dataset, which spans multiple low- and medium-voltage grid configurations, we conduct controlled experiments to isolate the effect of each inductive bias and assess both standard predictive performance and out-of-distribution generalization. Our study provides practical insights into which model assumptions most effectively guide learning for reliable and efficient voltage prediction in modern distribution networks.
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。