Skip to main navigation Skip to search Skip to main content

Discovering the Most Severe K-Point Failure Based on Reinforcement Learning: Preprint

Research output: Contribution to conference › Paper

Abstract

Smart devices are essential to ensure the stability of the power grid and resilience to intermittent energy production. However, smart devices can also be the target of cyber adversaries that may exploit false data injection attacks (FDIAs) to induce unstable grid conditions. A practical consideration of FDIA mitigation approaches is addressed here: given a finite available budget, for which smart device should cyber-threat mitigation be deployed first? In this work, this question is answered by identifying the so-called most-sensitive devices, i.e., the devices that, if compromised, can let an adversary induce the most serious grid instabilities. The method proposed utilizes an adversarial reinforcement learning (RL) framework to identify the k-mostsensitive smart devices (here, smart inverters). The adversarial agent can tamper with the compromised inverters' active and reactive operating power setup points, with the goal of maximizing voltage deviations. Numerical results show that the proposed RL method finds the optimal attack scenarios for 1-point failure and the near-optimal solution for the 2-point case. Additionally, the proposed RL method achieves an 8.8 speed-up ratio in running time compared to the brute force method for the 2-point case.
Original languageAmerican English
Number of pages9
StatePublished - 2026
EventThe 18th Annual IEEE Green Technologies (GreenTech) Conference - Boulder, CO USA
Duration: 25 Mar 2026 → 27 Mar 2026

Conference

ConferenceThe 18th Annual IEEE Green Technologies (GreenTech) Conference
CityBoulder, CO USA
Period25/03/26 → 27/03/26

Bibliographical note

See NLR/CP-2C00-100554 for paper as published in proceedings

NLR Publication Number

  • NLR/CP-2C00-97573

Keywords

  • false data injection attack
  • k-point failure
  • most sensitive inverts
  • reinforcement learning

Fingerprint

Dive into the research topics of 'Discovering the Most Severe K-Point Failure Based on Reinforcement Learning: Preprint'. Together they form a unique fingerprint.

Cite this