Discovery of False Data Injection Schemes on Frequency Controllers with Reinforcement Learning

TL;DR

This paper demonstrates how reinforcement learning can identify false data injection strategies on frequency controllers, exposing vulnerabilities in inverter-based energy resources that could lead to severe grid instability.

Contribution

It introduces a novel RL-based approach to discover cyber attack schemes targeting smart inverter frequency control systems, highlighting new security risks.

Findings

RL agent effectively finds optimal false data injection strategies

Injected data can destabilize frequency control, risking grid stability

Reveals critical vulnerabilities in inverter communication protocols

Abstract

While inverter-based distributed energy resources (DERs) play a crucial role in integrating renewable energy into the power system, they concurrently diminish the grid's system inertia, elevating the risk of frequency instabilities. Furthermore, smart inverters, interfaced via communication networks, pose a potential vulnerability to cyber threats if not diligently managed. To proactively fortify the power grid against sophisticated cyber attacks, we propose to employ reinforcement learning (RL) to identify potential threats and system vulnerabilities. This study concentrates on analyzing adversarial strategies for false data injection, specifically targeting smart inverters involved in primary frequency control. Our findings demonstrate that an RL agent can adeptly discern optimal false data injection methods to manipulate inverter settings, potentially causing catastrophic consequences.