Modular and Integrated AI Control Framework across Fiber and Wireless Networks for 6G

TL;DR

The paper addresses the need for unified, end-to-end AI-driven control in 6G networks that span wireless, transport, and optical domains. It proposes a modular AI control framework inspired by O-RAN near-RT RIC and extends it to the optical/transport layers, comprising an AI engine, a Register, two publish–subscribe message brokers, a Protocol Translation Module, and a Node Control Module, with support for decentralized collaboration across multiple controllers. The contributions include a detailed architectural blueprint, a node-and-AI app registration workflow, and mechanisms for cross-domain coordination and protocol translation, enabling self-configuring, self-monitoring, and self-repairing networks at scale. This framework has practical significance for enabling predictive capacity management and dynamic wavelength/channel optimization in multi-channel TWDM-PON environments, ultimately improving latency and QoS in future 6G networks.

Abstract

The rapid evolution of communication networks towards 6G increasingly incorporates advanced AI-driven controls across various network segments to achieve intelligent, zero-touch operation. This paper proposes a comprehensive and modular framework for AI controllers, designed to be highly flexible and adaptable for use across both fiber optical and radio networks. Building on the principles established by the O-RAN Alliance for near-Real-Time RAN Intelligent Controllers (near-RT RICs), our framework extends this AI-driven control into the optical domain. Our approach addresses the critical need for a unified AI control framework across diverse network transport technologies and domains, enabling the development of intelligent, automated, and scalable 6G networks.

Figures (2)

• Figure 1: System Architecture
• Figure 2: Node and AI control application registration and control workflow.