Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Decentralized Multi-Party Multi-Network AI for Global Deployment of 6G Wireless Systems

Merim Dzaferagic, Marco Ruffini, Nina Slamnik-Krijestorac, Joao F. Santos, Johann Marquez-Barja, Christos Tranoris, Spyros Denazis, Thomas Kyriakakis, Panagiotis Karafotis, Luiz DaSilva, Shashi Raj Pandey, Junya Shiraishi, Petar Popovski, Soren Kejser Jensen, Christian Thomsen, Torben Bach Pedersen, Holger Claussen, Jinfeng Du, Gil Zussman, Tingjun Chen, Yiran Chen, Seshu Tirupathi, Ivan Seskar, Daniel Kilper

TL;DR

The paper addresses the challenge of integrating AI across both radio and optical facets of 6G networks to enable end-to-end, zero-touch operation. It introduces the Decentralized Multi-party, Multi-network AI (DMMAI) framework, a control toolbox and architecture that coordinates AI-driven decisions across multiple network domains via O-RAN and similar controllers. Key contributions include a formal multi-network orchestration approach, an AI service management and orchestration layer, and the delineation of data and model repositories plus cross-AIC communication interfaces, designed to support scalable, swarm-inspired AI control. The work lays the groundwork for standardized reference use cases, data/model management practices, and benchmarking platforms to validate AI-enabled 6G solutions.

Abstract

Multiple visions of 6G networks elicit Artificial Intelligence (AI) as a central, native element. When 6G systems are deployed at a large scale, end-to-end AI-based solutions will necessarily have to encompass both the radio and the fiber-optical domain. This paper introduces the Decentralized Multi-Party, Multi-Network AI (DMMAI) framework for integrating AI into 6G networks deployed at scale. DMMAI harmonizes AI-driven controls across diverse network platforms and thus facilitates networks that autonomously configure, monitor, and repair themselves. This is particularly crucial at the network edge, where advanced applications meet heightened functionality and security demands. The radio/optical integration is vital due to the current compartmentalization of AI research within these domains, which lacks a comprehensive understanding of their interaction. Our approach explores multi-network orchestration and AI control integration, filling a critical gap in standardized frameworks for AI-driven coordination in 6G networks. The DMMAI framework is a step towards a global standard for AI in 6G, aiming to establish reference use cases, data and model management methods, and benchmarking platforms for future AI/ML solutions.

Decentralized Multi-Party Multi-Network AI for Global Deployment of 6G Wireless Systems

TL;DR

The paper addresses the challenge of integrating AI across both radio and optical facets of 6G networks to enable end-to-end, zero-touch operation. It introduces the Decentralized Multi-party, Multi-network AI (DMMAI) framework, a control toolbox and architecture that coordinates AI-driven decisions across multiple network domains via O-RAN and similar controllers. Key contributions include a formal multi-network orchestration approach, an AI service management and orchestration layer, and the delineation of data and model repositories plus cross-AIC communication interfaces, designed to support scalable, swarm-inspired AI control. The work lays the groundwork for standardized reference use cases, data/model management practices, and benchmarking platforms to validate AI-enabled 6G solutions.

Abstract

Multiple visions of 6G networks elicit Artificial Intelligence (AI) as a central, native element. When 6G systems are deployed at a large scale, end-to-end AI-based solutions will necessarily have to encompass both the radio and the fiber-optical domain. This paper introduces the Decentralized Multi-Party, Multi-Network AI (DMMAI) framework for integrating AI into 6G networks deployed at scale. DMMAI harmonizes AI-driven controls across diverse network platforms and thus facilitates networks that autonomously configure, monitor, and repair themselves. This is particularly crucial at the network edge, where advanced applications meet heightened functionality and security demands. The radio/optical integration is vital due to the current compartmentalization of AI research within these domains, which lacks a comprehensive understanding of their interaction. Our approach explores multi-network orchestration and AI control integration, filling a critical gap in standardized frameworks for AI-driven coordination in 6G networks. The DMMAI framework is a step towards a global standard for AI in 6G, aiming to establish reference use cases, data and model management methods, and benchmarking platforms for future AI/ML solutions.
Paper Structure (3 sections, 2 figures)

This paper contains 3 sections, 2 figures.

Table of Contents

  1. Introduction
  2. DMMAI Framework
  3. Conclusion

Figures (2)

  • Figure 1: dmmai Framework consists of an AI control toolbox that facilitates end-to-end AI services.
  • Figure 2: The AI controller or toolbox is composed of a set of repositories, virtual network functions, and interfaces. These interact with both user resources and x/rApps in order to carry out AI-based network functions/control.