Sionna Research Kit: A GPU-Accelerated Research Platform for AI-RAN
Sebastian Cammerer, Guillermo Marcus, Tobias Zirr, Fayçal Aït Aoudia, Lorenzo Maggi, Jakob Hoydis, Alexander Keller
TL;DR
Real-time AI/ML integration in 5G NR AI-RAN faces barriers of costly hardware and lack of practical testbeds. The Sionna Research Kit combines GPU-accelerated NVIDIA Jetson hardware with a software-defined OpenAirInterface stack to enable real-time AI-enhanced PHY processing and data collection. It presents a neural receiver trained with Sionna and deployed via TensorRT, along with a CUDA-accelerated LDPC decoder integrated into OAI, plus publicly available experiments and tutorials. This platform facilitates rapid prototyping, edge AI offloading, and realistic validation of AI-RAN concepts in live cellular networks.
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.