Supporting Intelligence in Disaggregated Open Radio Access Networks: Architectural Principles, AI/ML Workflow, and Use Cases

TLDR

O‑RAN is the leading open, programmable architecture for future wireless networks, with a global effort by the O‑RAN Alliance, operators, and research to standardize its building blocks. This paper aims to describe O‑RAN architecture and deployment status, present AI/ML capabilities and a telemetry framework, and analyze how AI/ML supports resource allocation and disaggregation in future O‑RANs. The authors implement supervised learning for traffic prediction and deep reinforcement learning for energy‑efficiency, illustrating the AI/ML workflow via xApps on the RIC and detailing the involved O‑RAN components. The study demonstrates that O‑RAN can host AI/ML by successfully deploying supervised learning for traffic prediction and deep reinforcement learning for energy‑efficiency, validating the proposed architecture.

Abstract

Driven by the emerging trend for transparent, open and programmable communications, Open Radio Access Network (O-RAN) constitutes the dominant architectural approach for deploying the future wireless networks. Towards standardizing and specifying the building blocks and principles of O-RAN, a coordinated global effort has been observed, mainly comprised of the O-RAN Alliance, the operators and several research activities. This paper presents the architectural aspects and the current status of O-RAN deployments, integrating both existing and ongoing activities from the O-RAN enablers. Furthermore, since the Artificial Intelligence and Machine Learning (AI/ML) act as key pillars for realizing O-RANs, a comprehensive view on the AI/ML functionality is provided as well. Additionally, a Network Telemetry (NT) architecture is also proposed to ensure end-to-end data collection and real-time analytics. To concretely illustrate the O-RAN supporting mechanisms for hosting AI/ML, we implemented two realistic ML algorithms: (i) a Supervised Learning (SL) based algorithm for cell traffic prediction using the training data of an open dataset and (ii) a Deep Reinforcement Learning (DRL) based algorithm for energy-efficiency maximization using a 5G-compliant simulator to obtain RAN measurements. We schematically demonstrate the AI/ML workflow for both ML-assisted algorithms through the usage of xApps running on the Radio Intelligent Controller (RIC), as well as we outline the role of the O-RAN components involved in the AI/ML loop. Combining the high-level architectural descriptions with a detailed presentation of ML-empowered resource allocation schemes, the paper discusses and summarizes the O-RAN disaggregation principles and the role of AI/ML embedded in future O-RAN deployments.