EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Distributed Event-Driven Serverless Platform for Multicluster IoT Environments

Hyungwoo Ju, Jangwon Seo, Younghan Kim iD

Sensors · 09.03.2026 · 26 (5) · 1718

DOI: 10.3390/s26051718 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 09.03.2026. Verfasst von Hyungwoo Ju und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronic Engineering, Soongsil University, Seoul 06978, Republic of Korea. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Development of Fast and Automatic Service recovery and Transition software in Hybrid Cloud Environment, Development of High Available and High Performance 6G Cross Cloud Infrastructure Technology, Korea governmen.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In modern smart city and IoT environments, diverse sensors for traffic management, environmental monitoring, and energy systems continuously generate large volumes of heterogeneous events in real time. Efficiently processing these multi-source event streams requires a scalable and responsive computing architecture. However, many Kubernetes-hosted serverless Function-as-a-Service (FaaS) deployments operate within a single administrative cluster and provide limited user-level control over dynamic multicluster placement based on heterogeneous event types and real-time resource conditions. To address these limitations, this study proposes a generalized event-driven FaaS architecture capable of efficiently processing multi-event streams across multicluster environments. The proposed architecture was implemented on Kubernetes-based testbed by integrating a multicluster orchestrator, an event-processing engine, a workflow execution layer, and a serverless platform. Evaluation using a smart city-inspired scenario demonstrates that the proposed platform provides improved load distribution characteristics and maintains higher workflow success rates under increasing workloads compared to the evaluated single-cluster baseline. This research provides a scalable design approach for serverless platforms that can meet real-time event processing requirements in IoT and smart city applications.

Schlagwörter

Stichwörter der Autor:innen

IoT systemsevent-driven systemmulti-eventreal-time processingserverless architecture

Autor:innen und Institutionen

  • School of Electronic Engineering, Soongsil University, Seoul 06978, Republic of Korea.

ORCID-Profile: Younghan Kim

Förderung

  • Development of Fast and Automatic Service recovery and Transition software in Hybrid Cloud Environment
  • Development of High Available and High Performance 6G Cross Cloud Infrastructure Technology
  • Korea governmen

Zitieren

APA

Ju, H., Seo, J., & Kim, Y. (2026). Distributed Event-Driven Serverless Platform for Multicluster IoT Environments. Sensors, 26(5), 1718. https://doi.org/10.3390/s26051718

Vancouver

Ju H, Seo J, Kim Y. Distributed Event-Driven Serverless Platform for Multicluster IoT Environments. Sensors. 2026;26(5):1718. doi:10.3390/s26051718

BibTeX
@article{Ju2026,
  author = {Ju, Hyungwoo and Seo, Jangwon and Kim, Younghan},
  title = {Distributed Event-Driven Serverless Platform for Multicluster IoT Environments},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {5},
  pages = {1718},
  doi = {10.3390/s26051718}
}
Kostenlos starten →