Nvidia wants telcos to ramp up 6G research — and it’s betting AI will be the key to future development

Nvidia has announced a new research platform that will help organizations accelerate the development of 6G technologies, the next generation of wireless technology.

The Nvidia Research Cloud platform will provide researchers with a “comprehensive suite to advance AI for use in radio access network (RAN) technology”, according to the announcement.

The platform will allow customers to simulate cloud communication environments in order to research 6G, which is expected to reach commercial viability nearer 2030.

Nvidia’s new platform boasts early adopters and partners such as Ansys, Arm, ETH Zurich, Fujitsu, Keysight, Nokia, Northeastern University, Rohde & Schwarz, Samsung, SoftBank Corp, and Viavi.

It will consist of three ‘foundational elements’, Nvidia Aerial Omniverse Digital Twin for 6G, Aerial CUDA-Accelerated RAN, and the Sionna Neural Radio Framework.

The Aerial Omniverse Digital Twin for 6G is a reference application that enables physically accurate simulations of 6G systems of various sizes, from a single tower to an entire city.

Researchers will be able to simulate and build base-station algorithms using site-specific data and train models in real time to boost transmission efficiency.

Testing and simulation are set to be key in the journey towards the next generation of wireless technology. As such, engineering software company Ansys announced it would be integrating its Perceive EM solver into the Omniverse ecosystem.

Nvidia’s Aerial CUDA-Accelerated RAN refers to a software-based full-RAN stack that offers researchers the freedom to customize, program, and test 6G networks in real time.

The Sionna Neural Network Framework integrates popular frameworks like PyTorch and TensorFlow, allowing users to leverage Nvidia GPUs to generate and capture data as well as training AI and ML models at scale.

Included in this package is Sionna, described by Nvidia as “the leading link-level research tool for AI/ML-based wireless simulations.”

Nvidia wants to drive the "next leap" in wireless communications

Nvidia boasted its 6G Research Cloud Platform is able to bring together these tools to help telecom companies unlock the full potential of 6G.

Charlie Zang, SVP of Samsung Research America, said the intersection of AI and 6G has the potential to be transformative, and could reimagine digital communication.

“The future convergence of 6G and AI holds the promise of a transformative technological landscape,” he explained

“This will bring seamless connectivity and intelligent systems that will redefine our interactions with the digital world, ushering in an era of unparalleled innovation and connectivity.”

SVP of Telecom at Nvidia, Ronnie Vasishta, said access to AI, a software-based full-RAN reference stack, and digital twin technology will be key in achieving the  transmission efficiencies required for the jump to 6G.

“The massive increase in connected devices and host of new applications in 6G will require a vast leap in wireless spectral efficiency in radio communications… Key to achieving this will be the use of AI, a software-defined, full-RAN reference stack and next-generation digital twin technology.”