EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Uncertainty-Aware LLM-Guided Cloud Resource Scheduling with Budgeted Robust Optimization

Amelia Turner

International Journal of Information and Communication Technology Trends · 2026

DOI: 10.66525/ijictt132 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Information and Communication Technology Trends, 2026. Verfasst von Amelia Turner. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Hybrid schedulers that let a large language model propose placements and a solver enforce feasibility have brought semantic reasoning into cluster resource management. Such pipelines still treat two quantities as exact: the model proposal itself, and the resource demands and runtimes attached to each task. Both are estimates, and a scheduler that ignores their error either over-trusts a wrong suggestion or packs a node to a capacity it does not have. This paper presents URSA, a scheduler that carries uncertainty through the whole decision path. Confidence in each model proposal is obtained from the agreement of temperature-diverse samples and mapped to a hit probability by post-hoc calibration, which then sets a per-task trust weight in the objective. Runtime prediction error is turned into finite-sample upper bounds by split conformal prediction at a level selected from each job's remaining deadline slack. Declared-versus-actual demand deviation is absorbed by a budgeted robust assignment program whose conservatism is controlled by a single parameter. Evaluation on real Spark TPC-H DAGs with measured task-duration profiles shows that URSA removes 95-96% of node memory-pressure and eviction events relative to a deterministic guided solver at equal job completion time, shortens makespan by 4-13%, and raises CPU utilization by up to 11%. Its behaviour stays flat as guidance reliability falls from 0.90 to 0.30 and under over-confident guidance, whereas the deterministic pipeline swings by up to 47% in utilization.

Zitieren

APA

Turner, A. (2026). Uncertainty-Aware LLM-Guided Cloud Resource Scheduling with Budgeted Robust Optimization. International Journal of Information and Communication Technology Trends. https://doi.org/10.66525/ijictt132

Vancouver

Turner A. Uncertainty-Aware LLM-Guided Cloud Resource Scheduling with Budgeted Robust Optimization. International Journal of Information and Communication Technology Trends. 2026. doi:10.66525/ijictt132

BibTeX
@article{Turner2026,
  author = {Turner, Amelia},
  title = {Uncertainty-Aware LLM-Guided Cloud Resource Scheduling with Budgeted Robust Optimization},
  journal = {International Journal of Information and Communication Technology Trends},
  year = {2026},
  doi = {10.66525/ijictt132}
}
Kostenlos starten →