Sionna Research Kit: A GPU-Accelerated Research Platform for AI-RAN

2025-05-19

AI Summary

To address the lack of efficient, low-cost, and reproducible experimental platforms for AI-RAN research, this work designs a GPU-accelerated hardware-software co-design platform based on the NVIDIA Jetson AGX Orin. The platform integrates the OpenAirInterface 5G NR protocol stack, the Sionna channel modeling framework, and the TensorRT inference engine, while maintaining full compatibility with the O-RAN architecture. It pioneers end-to-end neural receiver deployment—training in Sionna and real-time inference optimized via TensorRT—enabling, for the first time, closed-loop physical-layer validation on commercial 5G user equipment with 100+ Mbps throughput and sub-millisecond latency. The platform supports real-world channel data acquisition, edge AI model deployment, and rapid algorithm iteration. All source code and experimental examples are open-sourced, substantially lowering the barrier to entry for AI-RAN research.

Technology Category

• Machine Learning: Hardware-aware ML
• Planning, Routing, and Scheduling: Plan Execution and Monitoring
• Computer Vision: Remote Sensing / Geospatial AI

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

We introduce the NVIDIA Sionna Research Kit, a GPU-accelerated research platform for developing and testing AI/ML algorithms in 5G NR cellular networks. Powered by the NVIDIA Jetson AGX Orin, the platform leverages accelerated computing to deliver high throughput and real-time signal processing, while offering the flexibility of a software-defined stack. Built on OpenAirInterface (OAI), it unlocks a broad range of research opportunities. These include developing 5G NR and ORAN compliant algorithms, collecting real-world data for AI/ML training, and rapidly deploying innovative solutions in a very affordable testbed. Additionally, AI/ML hardware acceleration promotes the exploration of use cases in edge computing and AI radio access networks (AI-RAN). To demonstrate the capabilities, we deploy a real-time neural receiver - trained with NVIDIA Sionna and using the NVIDIA TensorRT library for inference - in a 5G NR cellular network using commercial user equipment. The code examples will be made publicly available, enabling researchers to adopt and extend the platform for their own projects.

Problem

• Developing AI/ML algorithms for 5G NR networks
• Enabling real-time signal processing with GPU acceleration
• Facilitating affordable AI-RAN and edge computing research

Innovation

• GPU-accelerated AI/ML platform for 5G
• Real-time signal processing with Jetson AGX
• OpenAirInterface-based flexible software stack