Self-healing power systems using reinforcement learning over graphs for controlled grid islanding

Sobhan Badakhshan

doi:10.1016/j.segan.2025.101937

Self-healing power systems using reinforcement learning over graphs for controlled grid islanding

2025-08-20

0

PRE

AI

DOI：10.1016/j.segan.2025.101937

Original

Original request for help

Save

Abstract

En 中文

• Develops a graph-based reinforcement learning model to improve grid resilience by enabling rapid restoration through intelligent switching. • Prevents collapse by isolating vulnerabilities and forming self-sustaining subsystems. • Considers generator inertia and load behavior for stable frequency control.

Keywords:

graph-based reinforcement learning

grid resilience

intelligent switching

self-sustaining subsystems

frequency control

Self-healing power systems using reinforcement learning over graphs for controlled grid islanding

Abstract

Journal

Organization