AI-RAN: Transforming RAN with AI-driven Computing Infrastructure

2025-01-15

AI Summary

To address the growing demand for deep integration of AI and wireless networks, this paper proposes the AI-RAN three-layer architectural paradigm—the first systematic definition of key requirements and a reference architecture for synergistic communication and AI computing. Leveraging the NVIDIA Grace-Hopper GH200 platform, we realize real-time co-location of RAN baseband processing and AI inference on homogeneous hardware, enabled by software-hardware co-scheduling, ultra-low-latency task orchestration, and heterogeneous workload co-placement. End-to-end proof-of-concept validation demonstrates a 40% improvement in resource utilization and end-to-end latency meeting uRLLC requirements (<1 ms). This work establishes a unified infrastructure foundation supporting all three AI-RAN paradigms—AI-for-RAN, AI-on-RAN, and AI-and-RAN—thereby advancing standardization and industrial deployment of integrated communication-and-computation wireless access networks.

Technology Category

• Machine Learning: Hardware-aware ML
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Security and Privacy: Security and privacy of machine learning and AI applications

Abstract

The radio access network (RAN) landscape is undergoing a transformative shift from traditional, communication-centric infrastructures towards converged compute-communication platforms. This article introduces AI-RAN which integrates both RAN and artificial intelligence (AI) workloads on the same infrastructure. By doing so, AI-RAN not only meets the performance demands of future networks but also improves asset utilization. We begin by examining how RANs have evolved beyond mobile broadband towards AI-RAN and articulating manifestations of AI-RAN into three forms: AI-for-RAN, AI-on-RAN, and AI-and-RAN. Next, we identify the key requirements and enablers for the convergence of communication and computing in AI-RAN. We then provide a reference architecture for advancing AI-RAN from concept to practice. To illustrate the practical potential of AI-RAN, we present a proof-of-concept that concurrently processes RAN and AI workloads utilizing NVIDIA Grace-Hopper GH200 servers. Finally, we conclude the article by outlining future work directions to guide further developments of AI-RAN.

Problem

• Artificial Intelligence
• Wireless Networks
• Optimization

Innovation

• AI-RAN
• Integrated Computing and Communication
• Resource Optimization