Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Towards Scalable Federated Container Orchestration: The CODECO Approach

Rute C. Sofia, Josh Salomon, Ray Carrol, Luis Garcés-Erice, Peter Urbanetz, Jürgen Gesswein, Rizkallah Touma, Alejandro Espinosa, Luis M. Contreras, Vasileios Theodorou, George Papathanail, Georgios Koukis, Vassilis Tsaoussidis, Alberto del Rio, David Jimenez, Efterpi Paraskevoulakou, Panagiotis Karamolegkos, John Soldatos, Borja Dorado Nogales, Alejandro Tjaarda

TL;DR

CODECO addresses cloud-centric limitations of Kubernetes in CEI by introducing a data–compute–network co-orchestration model and bounded federation via application neighborhoods. It couples centralized governance (OCM Hub) with decentralized execution and privacy-preserving learning (PDLC-FC) to enable context-aware, energy-conscious placement across heterogeneous edge-cloud environments. The architecture decomposes concerns into ACM-FC, SWM-FC, NetMA-FC, MDM-FC, PDLC-FC, and CODEF for reproducible experimentation, illustrating end-to-end workflows and run-time adaptation. The work demonstrates improved scalability, resilience to intermittent connectivity, and richer data/governance capabilities, while highlighting open challenges such as optimal aggregation in private federations and multi-hub federation.

Abstract

This paper presents CODECO, a federated orchestration framework for Kubernetes that addresses the limitations of cloud-centric deployment. CODECO adopts a data-compute-network co-orchestration approach to support heterogeneous infrastructures, mobility, and multi-provider operation. CODECO extends Kubernetes with semantic application models, partition-based federation, and AI-assisted decision support, enabling context-aware placement and adaptive management of applications and their micro-services across federated environments. A hybrid governance model combines centralized policy enforcement with decentralized execution and learning to preserve global coherence while supporting far Edge autonomy. The paper describes the architecture and core components of CODECO, outlines representative orchestration workflows, and introduces a software-based experimentation framework for reproducible evaluation in federated Edge-Cloud infrastructure environments.

Towards Scalable Federated Container Orchestration: The CODECO Approach

TL;DR

CODECO addresses cloud-centric limitations of Kubernetes in CEI by introducing a data–compute–network co-orchestration model and bounded federation via application neighborhoods. It couples centralized governance (OCM Hub) with decentralized execution and privacy-preserving learning (PDLC-FC) to enable context-aware, energy-conscious placement across heterogeneous edge-cloud environments. The architecture decomposes concerns into ACM-FC, SWM-FC, NetMA-FC, MDM-FC, PDLC-FC, and CODEF for reproducible experimentation, illustrating end-to-end workflows and run-time adaptation. The work demonstrates improved scalability, resilience to intermittent connectivity, and richer data/governance capabilities, while highlighting open challenges such as optimal aggregation in private federations and multi-hub federation.

Abstract

This paper presents CODECO, a federated orchestration framework for Kubernetes that addresses the limitations of cloud-centric deployment. CODECO adopts a data-compute-network co-orchestration approach to support heterogeneous infrastructures, mobility, and multi-provider operation. CODECO extends Kubernetes with semantic application models, partition-based federation, and AI-assisted decision support, enabling context-aware placement and adaptive management of applications and their micro-services across federated environments. A hybrid governance model combines centralized policy enforcement with decentralized execution and learning to preserve global coherence while supporting far Edge autonomy. The paper describes the architecture and core components of CODECO, outlines representative orchestration workflows, and introduces a software-based experimentation framework for reproducible evaluation in federated Edge-Cloud infrastructure environments.
Paper Structure (73 sections, 21 figures, 3 tables)

This paper contains 73 sections, 21 figures, 3 tables.

Table of Contents

  1. Introduction
  2. CODECO Design Principles and Scope
  3. Co-Orchestration Across Data, Compute, and Network
  4. Federation, Autonomy, Governance Model
  5. Context-awareness and Energy-aware Management
  6. Energy-awareness and Greenness Objectives
  7. Impact on Orchestration Decisions
  8. CODECO Federated Architecture
  9. Core Architectural Components
  10. Management Functions and Component Mapping
  11. Management Layers and Decision Timescales
  12. Federation and Control Structure
  13. Application Neighborhoods: Federated Partitioning
  14. Semantic Application Abstraction and Observability
  15. Federated Component Placement
  16. ...and 58 more sections

Figures (21)

  • Figure 1: The CODECO data-compute-network approach for deployment of applications and their micro-services across CEI. By observing the data workflow, the network and the computational resources, CODECO provides a finer-grained perspective on the IoT-Edge-Cloud infrastructure, thus providing a better support for the orchestration of applications across Edge-Cloud.
  • Figure 2: CODECO components and their high-level interactions.
  • Figure 3: CODECO components, positioning across federated clusters based on the Hub-and-spoke model of OCM. Green arrows represent the user to CODECO logic; red arrows represent the CODECO observability interfaces. Orange arrows correspond to the Hub to spoke control plan communication between CODECO components; blue arrows represent the communication between CODECO components across the control plane of MCs.
  • Figure 4: ACM-FC deployment across one Hub and two Managed Clusters.
  • Figure 5: ACM-FC and the neighborhood Manager.
  • ...and 16 more figures