EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SafeAgentGrid: A Hierarchical Constitutional Multi-Agent Framework for Trustworthy Autonomous Resource Optimization in Smart Energy Infrastructures

Noor Saeed Saleh, Maath Frman, Mustafa Noori, Kholood J. Moulood, Hachel Amer Ayash, Qutaiba Alasad

Network · 10.10.2026 · 6 (4) · 89

DOI: 10.3390/network6040089 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Network, online erschienen am 10.10.2026. Verfasst von Noor Saeed Saleh und 5 weiteren Autor:innen. Die Arbeit nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multi-agent reinforcement learning (MARL) has been increasingly utilized for the real-time control of smart energy infrastructures, where agents are still vulnerable to false data injection attacks (FDIAs), Byzantine failures, and specification misalignment. Existing constitutional AI techniques target discrete language-based coordination, not continuous-action cyber–physical control. In this paper, we propose SafeAgentGrid, a hierarchical neuro-symbolic constitutional framework. A projection filter guarantees every hard box-type constraint by construction. A hybrid neural-surrogate mediator combines a low-latency fast path, admitted only after a split-conformal test bounds its alignment shortfall, with a full path over a tightenedDC reachable set under fairness (Gini) and risk-aware security weighting. Finally, 8-bit quantized models support edge computing. In a data-informed DC power-flow simulation, SafeAgentGrid accomplishes an average reward of 200,186.9 at 0.0125±0.0014 violations/step, rising only to 0.0194±0.0016 under 20% FDIA and 0.0140±0.0015 under Byzantine failure of ⌊N/3⌋ agents, at 100% grid efficiency and 0.79 ms/step mediation latency. It enhances both reward and safety over four unmediated techniques trained in the same environment (Wilcoxon signed-rank, p≤3.4×10−8) on all ten training seeds and outperforms a joint safety shield and a Lagrangian constrained MARL technique, which violate the limits on 57.5% and 98.8% of the steps. We further derive the tightening from a chance constraint and show that it is necessary under the stochastic realization.

Zitieren

APA

Saleh, N. S., Frman, M., Noori, M., Moulood, K. J., Ayash, H. A., & Alasad, Q. (2026). SafeAgentGrid: A Hierarchical Constitutional Multi-Agent Framework for Trustworthy Autonomous Resource Optimization in Smart Energy Infrastructures. Network, 6(4), 89. https://doi.org/10.3390/network6040089

Vancouver

Saleh NS, Frman M, Noori M, Moulood KJ, Ayash HA, Alasad Q. SafeAgentGrid: A Hierarchical Constitutional Multi-Agent Framework for Trustworthy Autonomous Resource Optimization in Smart Energy Infrastructures. Network. 2026;6(4):89. doi:10.3390/network6040089

BibTeX
@article{Saleh2026,
  author = {Saleh, Noor Saeed and Frman, Maath and Noori, Mustafa and Moulood, Kholood J. and Ayash, Hachel Amer and Alasad, Qutaiba},
  title = {SafeAgentGrid: A Hierarchical Constitutional Multi-Agent Framework for Trustworthy Autonomous Resource Optimization in Smart Energy Infrastructures},
  journal = {Network},
  year = {2026},
  volume = {6},
  number = {4},
  pages = {89},
  doi = {10.3390/network6040089}
}
Kostenlos starten →