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.
This paper proposes a Neural Controlled Differential Equation (Neural CDE) framework for learning continuous-time surrogate models of grid-forming inverters for electromagnetic transient (EMT) simulation, which relaxes the constraint of fixed sampling rates and enables multi-time-scale control analysis.
An affine-control formulation with dual slow/fast pathways is introduced to capture the hierarchical and multiscale behavior of converter dynamics, and a physics-inspired regularization method is utilized to enhance stability and coherence.
Evaluated on EMT-generated trajectories, the model accurately reproduces transient responses, preserves effective damping and the dominant oscillatory characteristics, and maintains bounded long-horizon rollouts. The results show that Neural CDE-based component modeling offers a physically consistent surrogate modeling approach for EMT-level simulation studies.
Blogger's Review: This paper presents a novel Neural CDE framework that addresses the challenges in modeling power electronics by effectively managing multi-time-scale issues, enhancing model stability and coherence. Its application potential in electromagnetic transient analysis is noteworthy, promising to drive more efficient power system design and optimization in the future.