用物理约束神经网络模拟不公开的逆变器动态，提升电网仿真精度。
Physics-Informed Learning of Proprietary Inverter Models for Grid Dynamic Studies
- 融合物理规律与神经网络，学习逆变器内部未公开行为。
- 在电网形成逆变器案例中，仿真精度显著优于纯数据驱动方法。
- 适合电网稳定分析、控制参数调优等需要高精度模型的研究者。
本文提出一种基于物理信息神经微分方程的新框架，用于模拟不公开的逆变器动态，以提升电网动态仿真的准确性。当前工业实践中，设备制造商通常不披露逆变器内部控制策略与参数，导致精确动态仿真与稳定性分析中的增益调优等研究面临挑战。为此，我们设计了物理信息潜空间神经微分方程模型（PI-LNM），将系统物理规律与神经学习层结合，捕捉专有设备的未建模行为。该方法在电网形成逆变器（GFM）案例中得到验证，相比仅依赖数据驱动的模型，展现出更高的动态仿真精度。
原文摘要 · Abstract (English)
This letter develops a novel physics-informed neural ordinary differential equations-based framework to emulate the proprietary dynamics of the inverters -- essential for improved accuracy in grid dynamic simulations. In current industry practice, the original equipment manufacturers (OEMs) often do not disclose the exact internal controls and parameters of the inverters, posing significant challenges in performing accurate dynamic simulations and other relevant studies, such as gain tunings for stability analysis and controls. To address this, we propose a Physics-Informed Latent Neural ODE Model (PI-LNM) that integrates system physics with neural learning layers to capture the unmodeled behaviors of proprietary units. The proposed method is validated using a grid-forming inverter (GFM) case study, demonstrating improved dynamic simulation accuracy over approaches that rely solely on data-driven learning without physics-based guidance.
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。