Residual-Informed Learning of Solutions to Algebraic Loops
This work addresses simulation efficiency for large-scale systems like power grids, though it is incremental as it builds on existing neural network and residual-based methods.
The paper tackles the problem of replacing algebraic loops in Modelica models with neural network surrogates to speed up simulations, achieving a 60% reduction in simulation time for the IEEE 14-Bus system while maintaining accuracy.
This paper presents a residual-informed machine learning approach for replacing algebraic loops in equation-based Modelica models with neural network surrogates. A feedforward neural network is trained using the residual (error) of the algebraic loop directly in its loss function, eliminating the need for a supervised dataset. This training strategy also resolves the issue of ambiguous solutions, allowing the surrogate to converge to a consistent solution rather than averaging multiple valid ones. Applied to the large-scale IEEE 14-Bus system, our method achieves a 60% reduction in simulation time compared to conventional simulations, while maintaining the same level of accuracy through error control mechanisms.