用神经网络替代模型中的代数环，提升仿真速度60%。
Residual-Informed Learning of Solutions to Algebraic Loops
- 直接以残差作为损失函数训练神经网络，无需标注数据。
- 在IEEE 14节点系统上实现60%仿真加速，精度不变。
- 能稳定收敛到唯一解，避免多解平均问题，适合电力系统建模。
本文提出一种基于残差感知的机器学习方法，将方程模型中的代数环替换为神经网络代理模型。采用前馈神经网络，直接以代数环的残差（误差）作为损失函数进行训练，无需监督数据集。该策略同时解决了多解模糊问题，使代理模型能够收敛至一致解，而非多个有效解的平均值。在大型IEEE 14-Bus系统上的应用表明，该方法相比传统仿真实现60%的加速，同时通过误差控制机制保持相同精度。
原文摘要 · Abstract (English)
This paper presents a residual-informed machine learning approach for replacing algebraic loops in equation-based Modelica models with neural network surrogates. A feedforward neural network is trained using the residual (error) of the algebraic loop directly in its loss function, eliminating the need for a supervised dataset. This training strategy also resolves the issue of ambiguous solutions, allowing the surrogate to converge to a consistent solution rather than averaging multiple valid ones. Applied to the large-scale IEEE 14-Bus system, our method achieves a 60% reduction in simulation time compared to conventional simulations, while maintaining the same level of accuracy through error control mechanisms.
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。