NVIDIA Aerial Research Cloud (ARC) platform
OpenAirInterfaceTM (OAI) experts from Allbesmart have been working closely with NVIDIA and the OAI Software Alliance to integrate NVIDIA Aerial L1 with the OAI stack’s L2/L3 through the SCF FAPI (Small Cell Forum Functional API).
With the support of NVIDIA and the OAI Alliance, we have a dedicated team specializing in testing the NVIDIA ARC platform and maintaining an ARC reference implementation in our lab. Leveraging this expertise, we provide consultancy services to help organizations maximize the potential of NVIDIA ARC for cutting-edge AI-RAN research and experimentation.
- Configuration of the NVIDIA ARC network hardware
- Configuration of the gNB and CN servers
- Installation of the NVIDIA Aerial SDK
- Setup NVIDIA Aerial with OAI gNB and CN5G
- End-to-end validation with COTS UEs for maximum performance
- Support for new Aerial and OAI software releases
- Support for the NVIDIA Grace Hopper platform
- Guidance for AI-RAN use cases implementation
Source: adapted from AI-RAN Alliance
The Aerial Research Cloud (ARC) is the NVIDIA platform for 6G wireless research. It is a platform to enabling Artificial intelligence (AI) and Machine Learning (ML) algorithm design for autonomous networks and innovative air-interface design.
The NVIDIA Aerial SDK provides a cloud native virtual 5G wireless radio access network solution, with inline L1 GPU acceleration for 5G NR PHY processing. It supports gNB integration in O-RAN 7.2 split configuration with commercial RUs and UEs and is hosted on COTS servers. NVIDIA grants access to the CUDA source code for its Aerial SDK L1 stack, so together with the OAI L2+, this platform provides source code extending from the physical layer to the core network.
For detailed information please visit the NVIDIA ARC product page or contact us for support:
https://docs.nvidia.com/aerial/aerial-research-cloud/archive/1.2/text/product_brief/index.html