AI 中文总结
研究用物理信息神经网络对下垂控制的电网形成变流器动态行为建模，通过在合成数据上训练并与传统方法及普通神经网络对比，实现更高预测精度且大幅减少运行时间。
AI 中文摘要
本文研究物理信息神经网络用于下垂控制的电网形成变流器全动态行为建模。该方法在通过数值求解器生成的合成数据上训练，并与传统积分方法和普通神经网络进行基准测试。结果表明，与使用相同训练数据的普通网络相比，预测精度更高，与数值求解器相比，运行时间大幅减少。
英文摘要
This paper investigates physics-informed neural networks for modeling the full dynamic behavior of droop-controlled grid-forming converters. The approach is trained on synthetic data generated via numerical solvers and benchmarked against both traditional integration methods and a vanilla neural network. Results show higher predictive accuracy than the vanilla network using the same training data and substantially reduced runtime compared with numerical solvers.
CommentsThis work has been accepted by IFAC for publication under a Creative Commons license CC-BY-NC-ND
