Power electronic converter control is typically tuned per topology, limiting transfer across heterogeneous designs. This letter proposes a topology-agnostic meta-control framework that encodes converter netlists as typed bipartite graphs and uses a task-conditioned graph neural network backbone with distributed control heads. The policy is trained end-to-end via differentiable predictive control to amortize constrained optimal control over a distribution of converter parameters and reference-tracking tasks. In simulation on randomly sampled buck converters, the learned controller achieves near-optimal tracking performance relative to an online optimal-control baseline, motivating future extension to broader topologies, objectives, and real-time deployment.
@article{arxiv.2601.06686,
title = {A Power Electronic Converter Control Framework Based on Graph Neural Networks -- An Early Proof-of-Concept},
author = {Darius Jakobeit and Oliver Wallscheid},
journal= {arXiv preprint arXiv:2601.06686},
year = {2026}
}