Proactive AI-and-RAN Workload Orchestration in O-RAN Architectures for 6G Networks

2025-07-11

AI Summary

To address the resource coordination inefficiency arising from the conflict between RAN real-time requirements and AI computation intensity in 6G networks, this paper proposes an O-RAN-native AI-RAN convergence architecture. Methodologically, it introduces a Y1-interface-driven end-to-end dynamic coordination mechanism leveraging near-real-time RIC and xApps; designs a predictive resource orchestration framework integrating workload forecasting, anomaly detection, and Soft Actor-Critic reinforcement learning; and pioneers GPU Multi-Instance GPU (MIG) integration within O-RAN to enable fine-grained, elastic co-location of AI and RAN workloads. Evaluated via trace-driven simulation using real-world 5G traffic traces from Barcelona, the solution achieves a 99% RAN demand satisfaction rate, significantly improving resource utilization and service continuity under highly dynamic conditions. This work provides a practical, deployable technical pathway toward a unified intelligent 6G access platform.

Technology Category

• Machine Learning: Hardware-aware ML
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

The vision of AI-RAN convergence, as advocated by the AI-RAN Alliance, aims to unlock a unified 6G platform capable of seamlessly supporting AI and RAN workloads over shared infrastructure. However, the architectural framework and intelligent resource orchestration strategies necessary to realize this vision remain largely unexplored. In this paper, we propose a Converged AI-and-ORAN Architectural (CAORA) framework based on O-RAN specifications, enabling the dynamic coexistence of real-time RAN and computationally intensive AI workloads. We design custom xApps within the Near-Real-Time RAN Intelligent Controller (NRT-RIC) to monitor RAN KPIs and expose radio analytics to an End-to-End (E2E) orchestrator via the recently introduced Y1 interface. The orchestrator incorporates workload forecasting and anomaly detection modules, augmenting a Soft Actor-Critic (SAC) reinforcement learning agent that proactively manages resource allocation, including Multi-Instance GPU (MIG) partitioning. Using real-world 5G traffic traces from Barcelona, our trace-driven simulations demonstrate that CAORA achieves near 99% fulfillment of RAN demands, supports dynamic AI workloads, and maximizes infrastructure utilization even under highly dynamic conditions. Our results reveal that predictive orchestration significantly improves system adaptability, resource efficiency, and service continuity, offering a viable blueprint for future AI-and-RAN converged 6G systems.

Problem

• Dynamic coexistence of RAN and AI workloads in 6G
• Intelligent resource orchestration for O-RAN architectures
• Proactive management of GPU partitioning and RAN demands

Innovation

• Converged AI-and-ORAN Architectural (CAORA) framework
• Custom xApps in NRT-RIC for RAN monitoring
• SAC reinforcement learning for resource allocation