Hybrid Machine Learning Approach for Cyberattack Mitigation of Parallel Converters in a DC Microgrid - Detection and mitigation strategy for FDI attacks

Aug 5, 2026

Upload by Oliver

Cyberattack susceptibilities increase as communication requirements grow when more renewable energy sources are integrated into DC microgrids. Parallel DC-DC converters provide high current and supply loads, yet they remain vulnerable to attacks that can disrupt operation and destabilize the system. In particular, manipulation of communication commands and low-layer control signals may trigger voltage instability. This paper examines a cyberattack targeting parallel converters and proposes a hybrid machine learning detection and mitigation approach. Simulation results in MATLAB/Simulink confirm that the method identifies and blocks false data injection attacks, enabling safe microgrid operation.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages6

Reading Time15 min

AccessFree to download

Introduction

DC microgrids and secure control

Common cyber threats and FDIA

Traditional mitigation approaches

Hybrid Machine Learning Approach for Cyberattack Mitigation of Parallel Converters in a DC Microgrid Naser Souri, Graduate Student Member, IEEE, Ali Mehrizi-Sani, Senior Member, IEEE The Bradley Department of Electrical and Computer Engineering Virginia Tech, Blacksburg, VA 24061 e-mails: {nsouri,[mehrizi](mehrizi}@vt.edu)[}](mehrizi}@vt.edu)[@vt.edu](mehrizi}@vt.edu) arXiv :2406 .07503v1 [ ee ss . SY] 11 Jun 2024 Abstract—Cyberattack susceptibilities are introduced as the communication requirement increases with the incorporation of more renewable energy sources into DC microgrids. Parallel DCDC converters are utilized to provide high current and supply the load. Nevertheless, these systems are susceptible to cyberattacks that have the potential to disrupt operations and jeopardize stability. Voltage instability may result from the manipulation of communication commands and low-layer control signals. Therefore, in this paper, a cyberattack that specifically targets parallel DC-DC converters is examined in a DC microgrid. A hybrid machine learning-based detection and mitigation strategy is suggested as a means to counteract this threat. The false data injection (FDI) attack targeting the converters is investigated within a DC microgrid. The efficacy of the suggested approach is verified via simulations executed for various scenarios within the MATLAB/Simulink environment. The technique successfully identifies and blocks FDI attacks, preventing cyberattacks and ensuring the safe operation of the DC microgrid. Index Terms—Cyberattack, cybersecurity, DC microgrid, machine learning, LSTM, parallel converters. I. INTRODUCTION DC microgrids are emerged as a promising solution for integrating distributed renewable energy sources and energy storage systems into the power grid. [1] . Renewable sources generate DC power directly; therefore, they eliminate the need for conversion losses associated with AC transmission. Nevertheless, the extensive implementation of DC microgrids encounters several obstacles. An important obstacle is the guarantee of secure operation and control of the microgrid [2] . A general block diagram of a DC microgrid is shown in Fig. 1. As the demand for electricity increases and additional distributed sources are deployed, parallel converters become essential for effectively managing this evolving grid, which offers several benefits, such as modularity and scalability, and This work is supported in part by the National Science Foundation (NSF) under award ECCS-1953213, in part by the State of Virginia’s Commonwealth Cyber Initiative ([www.cyberinitiative.org](www.cyberinitiative.org)), in part by the U.S. Department of Energy’s Office of Energy Efficiency and Renewable Energy (EERE) under the Solar Energy Technologies Office Award Number 38637 (UNIFI Consortium led by NREL), and in part by Manitoba Hydro International. The views expressed herein do not necessarily represent the views of the U.S. Department of Energy or the United States Government. “© 20XX IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.” Fig. 1. General block diagram of a DC microgrid topology. promotes system redundancy in the grid. If one converter malfunctions, the others can continue to operate, maintain operation, and minimize interruptions. However, the increased complexity of a system with multiple interconnected converters requires resilient control and communication mechanisms in a smart grid. Reliance on communication networks and control systems for data exchange renders them susceptible to cyber threats [3] . By compromising communication networks or sensors, it could alter control si

FAQs

Why are parallel DC-DC converters in a DC microgrid vulnerable to cyberattacks?

They rely on communication commands and low-layer control signals, which can be manipulated. Such manipulation may cause voltage instability and disrupt operation.

What specific cyberattack does the paper focus on?

A false data injection (FDI) attack targeting the parallel DC-DC converters in a DC microgrid.

How does the proposed method mitigate the attack?

It uses a hybrid machine learning-based detection and mitigation strategy to identify and block FDI attacks, preventing cyberattacks from compromising safe operation.

Aug 5, 2026

Upload by Oliver