Saved in:
Bibliographic Details
Main Authors: Zheng, Jialin, Wang, Haoyu, Zeng, Yangbin, Xu, Han, Mou, Di, Li, Hong, Vazquez, Sergio, Franquelo, Leopoldo G.
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.03144
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908433753571328
author Zheng, Jialin
Wang, Haoyu
Zeng, Yangbin
Xu, Han
Mou, Di
Li, Hong
Vazquez, Sergio
Franquelo, Leopoldo G.
author_facet Zheng, Jialin
Wang, Haoyu
Zeng, Yangbin
Xu, Han
Mou, Di
Li, Hong
Vazquez, Sergio
Franquelo, Leopoldo G.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_03144
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Neural Substitute Solver for Efficient Edge Inference of Power Electronic Hybrid Dynamics
Zheng, Jialin
Wang, Haoyu
Zeng, Yangbin
Xu, Han
Mou, Di
Li, Hong
Vazquez, Sergio
Franquelo, Leopoldo G.
Systems and Control
Machine Learning
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.
title Neural Substitute Solver for Efficient Edge Inference of Power Electronic Hybrid Dynamics
topic Systems and Control
Machine Learning
url https://arxiv.org/abs/2507.03144