Topology-Aware Reinforcement Learning over Graphs for Resilient Power Distribution Networks

TL;DR

This paper presents a topology-aware graph reinforcement learning framework that uses topological data analysis to improve outage management and resilience in power distribution networks, achieving higher power delivery and fewer violations.

Contribution

It introduces a novel integration of topological data analysis with graph reinforcement learning for power network resilience, demonstrating significant performance improvements.

Findings

9-18% higher cumulative rewards

up to 6% increase in power delivery

6-8% fewer voltage violations

Abstract

Extreme weather events and cyberattacks can cause component failures and disrupt the operation of power distribution networks (DNs), during which reconfiguration and load shedding are often adopted for resilience enhancement. This study introduces a topology-aware graph reinforcement learning (RL) framework for outage management that embeds higher-order topological features of the DN into a graph-based RL model, enabling reconfiguration and load shedding to maximize energy supply while maintaining operational stability. Results on the modified IEEE 123-bus feeder across 300 diverse outage scenarios demonstrate that incorporating the topological data analysis (TDA) tool, persistence homology (PH), yields 9-18% higher cumulative rewards, up to 6% increase in power delivery, and 6-8% fewer voltage violations compared to a baseline graph-RL model. These findings highlight the potential of integrating RL with TDA to enable self-healing in DNs, facilitating fast, adaptive, and automated restoration.