A Comparative Study of Graph Representations for GNN-Based Power Grid Control in L2RPN

Adrian Degenkolb, Qiong Huang, Benjamin Schäfer
9/2/2026
cs.LG

No confident code implementation found for this paper.

Abstract

Graph construction is a critical but underexamined design choice in deep reinforcement learning for power grid control. We present a controlled experimental comparison of different graph representations, including physical topology, electrical-sensitivity, and hybrid variants for topology control in the Learning to Run a Power Network (L2RPN) environment. Our findings indicate that matching graph complexity to task granularity is more important than maximizing representational richness, and highlight the importance of controlled representation studies at scale.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Interpretable Policy Distillation for Power Grid Topology Control

86% match2026

Physics Informed Reinforcement Learning with Gibbs Priors for Topology Control in Power Grids

84% match2026

Learning Topology Actions for Power Grid Control: A Graph-Based Soft-Label Imitation Learning Approach

84% match2025

HUGO -- Highlighting Unseen Grid Options: Combining Deep Reinforcement Learning with a Heuristic Target Topology Approach

84% match2024

Managing power grids through topology actions: A comparative study between advanced rule-based and reinforcement learning agents

83% match1 repo132023

MxGPS: Multiplex Graph Transformers for a Power Grid Foundation Model

83% match2026

Cite this paper

@article{degenkolb2026comparative,
  title  = {A Comparative Study of Graph Representations for GNN-Based Power Grid Control in L2RPN},
  author = {Adrian Degenkolb and Qiong Huang and Benjamin Schäfer},
  year   = {2026},
  eprint = {2609.02538},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2609.02538v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2609.02538.svg)](https://codeofpaper.com/paper/2609.02538)

Discussion