Artificial Intelligence-Based Intrusion Detection Systems for Microgrids: A Systematic Literature Review
Journal of Intelligent Decision Making and Information Science · 10.10.2026 · 3 (16s) · 916-946
DOI: 10.17762/jidmis.v3.5009 ↗Kurz gefasst
Systematische Übersicht in der Zeitschrift Journal of Intelligent Decision Making and Information Science, online erschienen am 10.10.2026. Verfasst von Mohamed Hachimi. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Although the ongoing digitalization of microgrids increases the operational efficiency of distributed energy resources, it increases the vulnerability of these systems from the point of cyberattacks. Current literature reports many intrusion detection methods based on artificial intelligence; however, the nature of existing studies does not allow for the comparison of these methods as they include different attack scenarios, data sources, configurations, metrics, and validation settings. Consequently, the purpose of this investigation is to review the analogs of intrusion detection methods based on artificial intelligence. A systematic literature review was conducted on studies published from 2023 to September 2026 using IEEE Xplore, Scopus, and ScienceDirect. After duplicate removal, screening, and eligibility assessment following a structured review process, 22 primary studies were retained and classified according to artificial intelligence technique, attack type, microgrid type, detection function, learning paradigm, data source, validation environment, and performance metrics. The evidence suggests that deep learning methodologies, including convolutional neural networks (CNNs), recurrent neural networks (RNNs), and their hybrid variations, are the most common methodologies employed. The research shows that the primary threat studied is false data injection attacks, and simulations remain the primary validation method, although only a few publications incorporate real data, operational simulation, or physical testbeds. Some studies mention detection accuracy higher than 99%, but there are huge differences in data sets, the generation of attacks, classes, and evaluation methodologies. The studies displayed significant experimental results but little evidence of robust, transferable, and long-term application in practice.
Zitieren
APA
Hachimi, M. (2026). Artificial Intelligence-Based Intrusion Detection Systems for Microgrids: A Systematic Literature Review. Journal of Intelligent Decision Making and Information Science, 3(16s), 916-946. https://doi.org/10.17762/jidmis.v3.5009
Vancouver
Hachimi M. Artificial Intelligence-Based Intrusion Detection Systems for Microgrids: A Systematic Literature Review. Journal of Intelligent Decision Making and Information Science. 2026;3(16s):916-946. doi:10.17762/jidmis.v3.5009
BibTeX
@article{Hachimi2026,
author = {Hachimi, Mohamed},
title = {Artificial Intelligence-Based Intrusion Detection Systems for Microgrids: A Systematic Literature Review},
journal = {Journal of Intelligent Decision Making and Information Science},
year = {2026},
volume = {3},
number = {16s},
pages = {916--946},
doi = {10.17762/jidmis.v3.5009}
}
EUVIMED