EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Passive bandwidth estimation for fog computing

Kjeti Omang, Carsten Griwodz, Frank Johnsen

Norsk IKT-konferanse for forskning og utdanning · 2025

DOI: 10.5324/de4y1h80 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Norsk IKT-konferanse for forskning og utdanning, 2025. Verfasst von Kjeti Omang und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper investigates passive bandwidth estimation as ameans to improve scheduling in Kubernetes-based fog computing environments.In contrast to active probing techniques, passive methodsrely on observing existing traffic patterns to infer available bandwidth(ABW), offering a non-intrusive alternative suitable for dynamicand distributed systems. The study focuses on wired infrastructure networkswithin the cloud–fog–edge continuum. We develop and present an approach based on a modified version ofthe probe gap model, evaluated in an emulated network testbed. Tenexperiments were conducted under varying traffic conditions, packet lossrates, and link capacities. Timestamping artifacts and data filtering wereaddressed to ensure measurement integrity. The approach demonstratesreliable ABW estimation across all scenarios, confirming the viability ofpassive methods for bandwidth-aware scheduling in Kubernetes.

Zitieren

APA

Omang, K., Griwodz, C., & Johnsen, F. (2025). Passive bandwidth estimation for fog computing. Norsk IKT-konferanse for forskning og utdanning. https://doi.org/10.5324/de4y1h80

Vancouver

Omang K, Griwodz C, Johnsen F. Passive bandwidth estimation for fog computing. Norsk IKT-konferanse for forskning og utdanning. 2025. doi:10.5324/de4y1h80

BibTeX
@article{Omang2025,
  author = {Omang, Kjeti and Griwodz, Carsten and Johnsen, Frank},
  title = {Passive bandwidth estimation for fog computing},
  journal = {Norsk IKT-konferanse for forskning og utdanning},
  year = {2025},
  doi = {10.5324/de4y1h80}
}
Kostenlos starten →