Black-box modeling of PMSG-based wind energy conversion systems based on neural ODEs

Abstract

Integrating renewable energy sources like wind power into the power grid enhances the dynamic interactions among renewable energy-producing equipment, leading to new technological issues for the power grid. Modeling and simulation are essential to ensure the stability of the emerging power grid, but they require precise dynamic component modeling, which is often unavailable due to technical confidentiality and other factors. Conventional hardware-in-the-loop (HIL) simulation can accurately simulate the dynamics of a single renewable energy device, but not the complex dynamics of multiple devices. This research introduces a method that combines classical mechanism modeling and differential neural network modeling to create accurate wind turbine models utilizing equipment measurement data or HIL simulation data. A realistic wind turbine electromagnetic transient simulation model of a specific type is developed and validated by connecting it to the IEEE-39 node system, confirming the model’s accuracy.