A cost-constrained dismantling framework for hypergraph with dynamic cascading failure using deep reinforcement learning

Ting Jiang

doi:10.1016/j.physa.2025.130988

A cost-constrained dismantling framework for hypergraph with dynamic cascading failure using deep reinforcement learning

2025-09-24

0

PRE

AI

DOI：10.1016/j.physa.2025.130988

Original

Original request for help

Save

Abstract

En 中文

• Proposes a hypergraph capacity-load model to represent cascading failure phenomena. • Introduces a hypergraph dismantling model with cost constraints. • Presents C2HD-RL, a dynamic cascading hypergraph dismantling framework using deep RL. • C2HD-RL reduces hypergraph connectivity efficiently at lower attack cost.

A cost-constrained dismantling framework for hypergraph with dynamic cascading failure using deep reinforcement learning

Abstract

Journal

Organization