Vulnerability Identification and Remediation of FDI Attacks in Islanded DC Microgrids Using Multi-agent Reinforcement Learning

Ali Jafarian Abianeh, Yihao Wan, Farzad Ferdowsi, Nenad Mijatovic, Tomislav Dragicevic

    Research output: Contribution to journalJournal articleResearchpeer-review

    230 Downloads (Pure)

    Abstract

    This paper proposes a novel approach to uncover deficiencies of the existing cyber-attack detection schemes and thereby to serve as a foundation for establishing more reliable cybersecure solutions, with particular application in DC microgrids. For this purpose, a multi-agent deep Reinforcement Learning (RL) based algorithm is proposed to automatically discover the vulnerable spots on the conventional index-based cyberattack detection schemes, and automatically generate coordinated stealthy destabilizing False Data Injection (FDI) attacks on cyberprotected islanded DC microgrids. To enable a continuous action space for the trained RL agents and enhance the algorithm’s precision and convergence rate, Deep Deterministic Policy Gradient DDPG) is incorporated. Using this approach, susceptibility of a state-of-the-art detection scheme to several different coordinated FDI attacks on the distributed communication links is identified. The proposed algorithm is also enhanced with a sniffing feature to enable maintaining the stealthy attacks even under the sudden disconnection of any of the compromised links. To address the discovered deficiencies within the index-based detection scheme, a complementary multi-agent RL detection algorithm using Deep Q-Network (DQN) is integrated, which provides a more reliable overall identification performance. Taking into account the communication delays and load changes, the effectiveness of the proposed algorithm is verified by the experimental tests.
    Original languageEnglish
    Article number9633178
    JournalIEEE Transactions on Power Electronics
    Volume37
    Issue number6
    Pages (from-to)6359-6370
    Number of pages12
    ISSN0885-8993
    DOIs
    Publication statusPublished - 2022

    Keywords

    • Distributed Control
    • DC Microgrid
    • Cybersecurity
    • False Data Injection
    • Reinforcement Learning

    Fingerprint

    Dive into the research topics of 'Vulnerability Identification and Remediation of FDI Attacks in Islanded DC Microgrids Using Multi-agent Reinforcement Learning'. Together they form a unique fingerprint.

    Cite this