An AI-Based Supervisory Measurement Integrity Validation Layer for Cyber-Resilient AC/DC Protection in Inverter-Based Microgrids

2026-04-26

AI Summary

This study addresses the vulnerability of line current differential protection in inverter-based microgrids to false data injection attacks that compromise measurement integrity. To counter this threat, the authors propose a supervised, artificial intelligence–driven measurement validation method that leverages the physical consistency inherent in synchronized instantaneous current waveforms. By employing an offline-trained recurrent neural network to analyze the temporal structural characteristics of differential currents in real time, the approach achieves high-fidelity attack detection without requiring additional sensors, system topology information, or modifications to existing relays, rendering it applicable to both AC and DC microgrids. Experimental results demonstrate consistently high detection accuracy across diverse fault and attack scenarios, and hardware-in-the-loop testing confirms that the method meets stringent protection timing constraints, underscoring its practical deployability.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Hardware-aware ML
• Humans and AI: Human-in-the-loop Machine Learning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Line current differential relays (LCDRs) are measurement-driven relays that rely on time-synchronized multi-phase current waveforms to infer internal faults in AC and DC power networks. In inverter-based microgrids, however, the increasing reliance on digitally communicated measurements exposes LCDRs to false-data injection attacks (FDIAs), in which adversaries manipulate remote measurement streams to create protection-triggering yet physically inconsistent current trajectories. This paper addresses this emerging measurement integrity problem by introducing a measurement integrity validation scheme that operates as a supervisory instrumentation layer for modern LCDRs. The proposed scheme interprets short windows of synchronized instantaneous current measurements recorded during relay operation and assesses their physical consistency to distinguish genuine fault-induced trajectories from cyber-manipulated measurement streams. A recurrent neural network is trained offline using only relay-available current measurements and exploits the temporal structure of differential current waveforms, which remains informative in inverter-dominated systems where current magnitude is no longer a reliable observable. The method requires no additional sensors, auxiliary protection elements, or prior knowledge of network topology, and is applicable to both AC and DC LCDRs without structural modification. The proposed measurement validation scheme is evaluated on an islanded inverter-based microgrid under a comprehensive set of fault and FDIA scenarios, demonstrating high detection accuracy while preserving relay dependability. Hardware-in-the-loop validation using an OPAL-RT real-time simulator confirms that the scheme satisfies protection timing constraints and can operate in real time under realistic operating conditions.

Problem

• false-data injection attacks
• measurement integrity
• inverter-based microgrids
• current differential relays
• cyber-resilient protection

Innovation

• measurement integrity validation
• false data injection attack
• recurrent neural network
• inverter-based microgrid
• line current differential relay