Neural Substitute Solver for Efficient Edge Inference of Power Electronic Hybrid Dynamics
This work addresses the problem of real-time edge inference for power electronic systems, enabling improved testing, control, and monitoring, and is incremental as it builds on neural networks to enhance existing solver methods.
The paper tackled the challenge of efficiently inferring hybrid continuous-discrete dynamics in power electronic systems on resource-constrained edge hardware by proposing a neural substitute solver (NSS) framework, which achieved a 23x speedup and 60% hardware resource reduction compared to traditional solvers.
Advancing the dynamics inference of power electronic systems (PES) to the real-time edge-side holds transform-ative potential for testing, control, and monitoring. How-ever, efficiently inferring the inherent hybrid continu-ous-discrete dynamics on resource-constrained edge hardware remains a significant challenge. This letter pro-poses a neural substitute solver (NSS) approach, which is a neural-network-based framework aimed at rapid accurate inference with significantly reduced computational costs. Specifically, NSS leverages lightweight neural networks to substitute time-consuming matrix operation and high-order numerical integration steps in traditional solvers, which transforms sequential bottlenecks into highly parallel operation suitable for edge hardware. Experimental vali-dation on a multi-stage DC-DC converter demonstrates that NSS achieves 23x speedup and 60% hardware resource reduction compared to traditional solvers, paving the way for deploying edge inference of high-fidelity PES dynamics.