Tutorials

Deployment of AI/ML components in the physical layer of a real 5G system can be a challenging yet exciting task. The Sionna Research Kit provides a set of tutorials and code examples on how to deploy your own AI-RAN components in a real 5G network using commercial-off-the-shelf (COTS) hardware.

In a first step, we show how the physical layer can be accelerated using GPU-Accelerated LDPC Decoding. The tutorial on Plugins & Data Acquisition explains how to capture and record real-world 5G signals using the Sionna Research Kit. As next step, the Integration of a Neural Demapper tutorial explains how to train a neural network-based demapper and integrate it in the 5G stack using NVIDIA TensorRT for real-time inference. Finally, the Software-defined End-to-End 5G Network tutorial allows to simulate the entire end-to-end system using software defined user equipment (UE). This allows for the evaluation of novel — non-standard compliant — algorithms and protocols.

All tutorials are precompiled during the quickstart setup of the system, and integrated in the compiled images. Check Running the Tutorials if you want to give them a try before going into the details.

Additionally, we provide a tutorial on Debugging & Troubleshooting to help you resolve issues that may arise when working with the Sionna Research Kit.

Besides AI for RAN, the AI-RAN alliance also envisions the coexistence of AI and RAN on the same platform. Many examples of LLM deployment on the Jetson platform can be found in the NVIDIA Jetson AI Lab.

You can find all tutorials below:

• Running the Tutorials
• GPU-Accelerated LDPC Decoding
• Plugins & Data Acquisition
• Integration of a Neural Demapper
• Software-defined End-to-End 5G Network
• Debugging & Troubleshooting

The best way to get started is to have a look at the Running the Tutorials section.