Continuous QoS-compliant Orchestration in the Cloud-Edge Continuum

TL;DR

FogArm tackles the challenge of continuously enforcing QoS‑aware decisions for multiservice applications in the Cloud‑Edge continuum. It fuses FogMon for real‑time infrastructure monitoring with FogBrainX for incremental reasoning and deploys decisions through Docker Swarm, ensuring ongoing alignment with CI/CD pipelines. The work demonstrates scalable orchestration across a distributed Italian testbed and shows that continuous reasoning reduces migration loads and decision time compared with exhaustive approaches. This approach enables proactive, automated management of dynamic edge environments, improving QoS guarantees and reducing operational overhead in multi‑service deployments.

Abstract

The problem of managing multi-service applications on top of Cloud-Edge networks in a QoS-aware manner has been thoroughly studied in recent years from a decision-making perspective. However, only a few studies addressed the problem of actively enforcing such decisions while orchestrating multi-service applications and considering infrastructure and application variations. In this article, we propose a next-gen orchestrator prototype based on Docker to achieve the continuous and QoS-compliant management of multiservice applications on top of geographically distributed Cloud-Edge resources, in continuity with CI/CD pipelines and infrastructure monitoring tools. Finally, we assess our proposal over a geographically distributed testbed across Italy.

Figures (6)

• Figure 1: Bird’s-eye view of FogArm.
• Figure 4: The WebGUI.
• Figure 5: FogArm's UML interaction diagram.
• Figure 6: Example application.
• Figure 7: Results for the scalability assessment.