EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

LLM-Conductor: A Closed-Loop Resource-Adaptive Architecture for Secure LLM Deployment in Industrial Sensor Networks and IIoT Systems

Kai Xu, Diming Zhang, Xuguo Wang

Sensors · 28.04.2026 · 26 (9) · 2733

DOI: 10.3390/s26092733 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 28.04.2026. Verfasst von Kai Xu und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Engineering, Jiangsu University of Science and Technology, Zhenjiang 212100, China. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To address the bottlenecks of missing decision-making closed loop, insufficient experience reuse, and decoupled resource scheduling in industrial LLM deployment, this paper proposes LLM-Conductor, a three-layer collaborative architecture that enables monitoring-feedback autonomous decision-making, structured policy memory, and joint policy-resource optimization.Through ablation studies, horizontal comparisons with ISOLATEGPT and ReAct, and graded resource-reduction experiments across six tiers, the results demonstrate that the security risk incidence rate is reduced from 70.6 percent to 1.3 percent, the multi-application collaborative task completion rate reaches 100 percent, and token utilization improves to 88.9 percent. Under constraints of at least 512 MB memory and at least 0.5 GHz CPU, the core task completion rate remains above 95 percent. By deeply coupling decision-making with resource scheduling, this architecture provides an integrated pathway toward efficient, secure, and reliable LLM deployment in Industrial Internet of Things scenarios. Current validation focuses on software-layer interaction patterns under simulated resource-constrained environments, with physical-layer industrial integration reserved for future work.

Schlagwörter

Stichwörter der Autor:innen

LLM securityclosed-loop controlindustrial deploymentindustrial environment simulation and adaptationresource optimization

Autor:innen und Institutionen

  • School of Computer Science and Engineering, Jiangsu University of Science and Technology, Zhenjiang 212100, China.
  • State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210046, China.

Zitieren

APA

Xu, K., Zhang, D., & Wang, X. (2026). LLM-Conductor: A Closed-Loop Resource-Adaptive Architecture for Secure LLM Deployment in Industrial Sensor Networks and IIoT Systems. Sensors, 26(9), 2733. https://doi.org/10.3390/s26092733

Vancouver

Xu K, Zhang D, Wang X. LLM-Conductor: A Closed-Loop Resource-Adaptive Architecture for Secure LLM Deployment in Industrial Sensor Networks and IIoT Systems. Sensors. 2026;26(9):2733. doi:10.3390/s26092733

BibTeX
@article{Xu2026,
  author = {Xu, Kai and Zhang, Diming and Wang, Xuguo},
  title = {LLM-Conductor: A Closed-Loop Resource-Adaptive Architecture for Secure LLM Deployment in Industrial Sensor Networks and IIoT Systems},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {9},
  pages = {2733},
  doi = {10.3390/s26092733}
}
Kostenlos starten →