← Back to all news
arXiv AI By Jiagang Qu, Yong Tao, Dan Wang, Enyi Li, Jingjing Qi, Ding Wang

Neural Controlled Differential Equations for EMT-Level Surrogate Modeling of Grid-Forming Inverters

Read the original on arXiv AI →

arXiv:2607. 16258v1 Announce Type: cross Abstract: The application of artificial intelligence methods in power electronic converter modeling is becoming increasingly widespread, but existing applications still face many challenges, such as difficulties in multi-time-scale hybrid analysis and the lack of physics-aware evaluation criteria and constraints, resulting in poor performance.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Aug 11

Tools to Explain Neural Networks for Power System Dynamics

arXiv:2608. 08048v1 Announce Type: cross Abstract: This paper presents, for the first time in power systems literature to our knowledge, analytical tools to explain the training performance of machine learning surrogate models for power system dynamics.

By Petros Ellinas, Johanna Vorwerk, Spyros Chatzivasileiadis
More like this →
arXiv Machine Learning
Sep 25

RAPTOR: RAndom-projection Physics-informed Transient sOlveR

RAPTOR is a novel time‑domain simulation framework for power systems that uses a physics‑informed random‑projection neural network built from fixed Gaussian radial basis functions to represent the trajectory of hybrid differential‑algebraic equations over a time interval. By combining these basis functions with a nonlinear solver such as Newton‑Raphson, RAPTOR can capture complex multi‑timescale dynamics over longer intervals, reducing the number of simulation advances and nonlinear iterations needed. Numerical tests on RMS and EMT benchmarks demonstrate that RAPTOR achieves accurate solutions with significantly fewer steps and can outperform traditional methods like Radau and the trapezoidal rule, achieving speedups of over tenfold in some cases.

By Petros Ellinas, Benjamin Vilmann, Spyros Chatzivasileiadis, Johanna Vorwerk
benchmarks
More like this →