Enhancing Fog IoT Container Deployment: A Customizable Kubernetes Scheduler
In an era where the Internet of Things (IoT) is becoming integral to daily life, the demand for efficient computing solutions is rapidly increasing, and the orchestration of containers in fog computing environments has emerged as a critical area of research. Single-Board Computers (SBCs) are particu...
| Autores: | , , |
|---|---|
| Tipo de recurso: | artículo |
| Fecha de publicación: | 2025 |
| País: | España |
| Institución: | Universidad de Castilla-La Mancha |
| Repositorio: | RUIdeRA. Repositorio Institucional de la UCLM |
| OAI Identifier: | oai:ruidera.uclm.es:10578/45093 |
| Acceso en línea: | https://doi.org/10.1016/j.future.2025.108195 https://hdl.handle.net/10578/45093 |
| Access Level: | acceso abierto |
| Palabra clave: | Customizable orchestrator Fog-IoT environments Kubernetes Workload scheduling |
| Sumario: | In an era where the Internet of Things (IoT) is becoming integral to daily life, the demand for efficient computing solutions is rapidly increasing, and the orchestration of containers in fog computing environments has emerged as a critical area of research. Single-Board Computers (SBCs) are particularly well-suited to fog computing environments due to their low cost, energy efficiency, and local processing capabilities. However, the efficient orchestration of containerized applications on these resource-constrained machines at the cost of performance is still an open issue. This paper presents Chronos (Customizable Heuristic Resource Orchestrator for Node Optimization Scheduling), a customizable scheduling framework for Kubernetes designed to overcome existing architectural limitations. The framework features a programmable scheduling operator with advanced monitoring capabilities, enabling system administrators to adapt scheduling policies to application-specific needs. It operates by harnessing real-time telemetry and time-series performance data. Chronos was deployed on a realistic SBC testbed with representative services and synthetic workloads simulating user behavior. Experimental results show that Chronos improves performance and resource utilization over baseline scheduling algorithms. In particular, when compared to the default Kubernetes scheduler, Chronos customized scheduler was able to reduce network latency up to 23 % for network-intensive workloads, disk write operations up to 42 % for disk-intensive workloads, and response time up to 20 % for CPU-intensive workloads, while maintaining low overhead |
|---|