NVIDIA
NVIDIA’s 6G Research Cloud platform empowers researchers with a novel approach to develop the next phase of wireless technology.

Research Cloud Platform to Advance 6G Development

March 20, 2024
The NVIDIA 6G Research Cloud offers developers a comprehensive suite to advance radio-access-network technology.

What you’ll learn:

  • What is the NVIDIA 6G Research Cloud platform? 
  • How it can benefit wireless development and 6G applications.

Offering a way to accelerate 6G development with technologies to connect myriad devices in cloud infrastructures, the open, flexible, and interconnected NVIDIA 6G Research Cloud platform is a comprehensive suite to advance AI for radio-access-network (RAN) technology. It helps establish the foundation for cloud-supported intelligent systems, autonomous vehicles, smart spaces, and a variety of augmented- and virtual-reality solutions, as well as immersive education tools and collaborative robotics.

The quick maturation of AI technology is also impacting 6G research—6G will probably be the first wireless protocol to be fully AI-capable. This will require validating new AI algorithmic approaches to optimize and increase network capacity and speed. Next-generation usage types require emulating realistic network conditions at scale, with tools that realistically simulate every part of a wireless system to refine AI algorithms for commercialization.  

“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,” said Ronnie Vasishta, senior vice president of telecom at NVIDIA. “Key to achieving this will be the use of AI, a software-defined, full-RAN reference stack, and next-generation digital twin technology.”

Inside the NVIDIA 6G Research Cloud Platform

The NVIDIA 6G Research Cloud platform is made up of three building blocks: Aerial Omniverse Digital Twin for 6G, Aerial CUDA-Accelerated RAN, and Sionna Neural Radio Framework. The Aerial Omniverse Digital Twin for 6G is a reference application with a developer sample to enable accurate simulations of 6G systems from a single tower to an entire city. Omniverse Digital Twin combines software-defined RAN and user-equipment simulators with realistic terrain and object properties to simulate and build base-station algorithms using site-specific data for training models in real-time.

It works along with Aerial CUDA-Accelerated RAN, a flexible software-defined stack for customizing, programming, and testing 6G networks in real-time. The Sionna Neural Radio Framework provides seamless integration with frameworks like PyTorch and TensorFlow, using NVIDIA GPUs to generate and capture data to train AI and machine-learning models at scale. This is also supported by NVIDIA Sionna, a sophisticated link-level research tool for AI/ML-based wireless simulations.

Testing is Essential

Testing and simulation are essential in developing these next-generation wireless platforms, and as such, leading providers in T&M are working with NVIDIA, such as Ansys and Keysight. These partnerships are helping the NVIDIA 6G Research Cloud platform to empower telcos and unlock the full potential of 6G, paving the way for next-gen wireless technology. 

According to Shawn Carpenter, program director of 5G/6G and space at Ansys, “Ansys is committed to advancing the mission of the 6G Research Cloud by seamlessly integrating the cutting-edge Ansys Perceive EM solver into the Omniverse ecosystem. Perceive EM revolutionizes the creation of digital twins for 6G systems. Undoubtedly, the convergence of NVIDIA and Ansys technologies will pave the way toward AI-enabled 6G communication systems.”

Keysight Technologies’ portfolio of network emulation solutions will enable developers to create and validate approaches to optimize wireless communications using the company’s full suite of network emulation solutions. The company is making cloud-based versions of its emulation solutions to make them available on the research platform in a flexible and scalable manner. 

"We are thrilled to be one of the first solution partners announced for NVIDIA's new 6G Research Cloud platform," said Kailash Narayanan, Senior Vice President and President of Keysight's Communications Solutions Group. "By integrating our solutions onto this cloud-based platform, researchers will have access to fast, scalable versions of the industry's most realistic network emulation capabilities. This level of realism and scalability will be essential for developing AI architectures capable of optimizing next-gen wireless systems."

Ronnie Vasishta, Senior Vice President of Telecom at NVIDIA, added, "An open and modular cloud-based platform is necessary for 6G researchers to trial new AI algorithms and techniques using a platform that enables simulation with physically accurate digital twins and an accelerated RAN software stack. As we expand a rich ecosystem of technologies that can address a wide variety of research needs, spanning academia and industry, we welcome Keysight as one of the first solution providers to our 6G Research Cloud platform."

Related links:

Sponsored Recommendations

UHF to mmWave Cavity Filter Solutions

April 12, 2024
Cavity filters achieve much higher Q, steeper rejection skirts, and higher power handling than other filter technologies, such as ceramic resonator filters, and are utilized where...

Wideband MMIC Variable Gain Amplifier

April 12, 2024
The PVGA-273+ low noise, variable gain MMIC amplifier features an NF of 2.6 dB, 13.9 dB gain, +15 dBm P1dB, and +29 dBm OIP3. This VGA affords a gain control range of 30 dB with...

Fast-Switching GaAs Switches Are a High-Performance, Low-Cost Alternative to SOI

April 12, 2024
While many MMIC switch designs have gravitated toward Silicon-on-Insulator (SOI) technology due to its ability to achieve fast switching, high power handling and wide bandwidths...

Request a free Micro 3D Printed sample part

April 11, 2024
The best way to understand the part quality we can achieve is by seeing it first-hand. Request a free 3D printed high-precision sample part.