EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An Explainable Ai Framework for Multi-Class Attack Classification in Mqtt-Coap-Based Hybrid Energy Monitoring Networks

Ahmed Fakhri Abdullah, Omar Ahmed Razooqi, Oras Fadhil Khalaf, Ayman AbuBaker, Amer Alqutaish, Saidah Khan

Babylonian Journal of Machine Learning · 07.11.2026 · 2026 · 274-312

DOI: 10.58496/bjml/2026/017 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Babylonian Journal of Machine Learning, online erschienen am 07.11.2026. Verfasst von Ahmed Fakhri Abdullah und 5 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Hybrid renewable-energy microgrids communicate through lightweight MQTT and CoAP links, exposing network traffic and sensor measurements to cyberattacks. This study presents an explainable framework for multi-class attack classification using reproducible message-level co-simulation of a photovoltaic–wind–diesel–battery microgrid. The simulation incorporates exact power balance, eleven sensors, six attack families, and five categories of challenging benign events. The dataset contains 86,400 thirty-second windows spanning 30 days, including 878 attack bursts. Sixty-eight features combine traffic statistics with energy-consistency residuals calibrated during a clean commissioning interval. Evaluation uses chronological partitioning, a purge gap, and block-bootstrap confidence intervals. Among seven classifiers, boosted trees with a five-window lag achieve a macro-F1 of 0.913 (95% confidence interval: 0.893–0.927), Matthews correlation coefficient of 0.907, accuracy of 0.978, and macro-averaged ROC-AUC of 0.974 on seven unseen days. Random partitioning inflates false-data-injection F1 by up to 13 percentage points. All bursts across five network-visible attack classes are detected, with class F1 scores of 0.93–0.98 and a 1.2% false-alarm rate on normal windows. However, window-level detection rates for false-data injection fall to 81% for bias attacks, 65% for ramp attacks, and at most 10% for energy-balance-preserving attacks. Halving attack intensity reduces macro-F1 by five percentage points, while transfer to a second site produces a twelve-point reduction before local adaptation. TreeSHAP explanations demonstrate faithfulness and stability, with deletion AUC of 0.22 versus 0.51 for random rankings, top-five overlap of 0.89, and approximately one-millisecond computation per window. These simulation-based findings highlight both classification effectiveness and limitations under stealthy attacks and site changes; code and data are released for replication.

Zitieren

APA

Abdullah, A. F., Razooqi, O. A., Khalaf, O. F., AbuBaker, A., Alqutaish, A., & Khan, S. (2026). An Explainable Ai Framework for Multi-Class Attack Classification in Mqtt-Coap-Based Hybrid Energy Monitoring Networks. Babylonian Journal of Machine Learning, 2026, 274-312. https://doi.org/10.58496/bjml/2026/017

Vancouver

Abdullah AF, Razooqi OA, Khalaf OF, AbuBaker A, Alqutaish A, Khan S. An Explainable Ai Framework for Multi-Class Attack Classification in Mqtt-Coap-Based Hybrid Energy Monitoring Networks. Babylonian Journal of Machine Learning. 2026;2026:274-312. doi:10.58496/bjml/2026/017

BibTeX
@article{Abdullah2026,
  author = {Abdullah, Ahmed Fakhri and Razooqi, Omar Ahmed and Khalaf, Oras Fadhil and AbuBaker, Ayman and Alqutaish, Amer and Khan, Saidah},
  title = {An Explainable Ai Framework for Multi-Class Attack Classification in Mqtt-Coap-Based Hybrid Energy Monitoring Networks},
  journal = {Babylonian Journal of Machine Learning},
  year = {2026},
  volume = {2026},
  pages = {274--312},
  doi = {10.58496/bjml/2026/017}
}
Kostenlos starten →