VIAVI makes strides in 6G & AI research with city-scale digital twin

VIAVI Solutions Inc. has announced major progress in its 6G and Artificial Intelligence (AI) research. These developments are primarily based on the company's 6G Forward Program, which aims to cement the future of wireless communications which is expected to be heavily influenced by AI.

This research has led to the unveiling of a city-scale digital twin, an integral data source for training other network elements such as the 6G AI-Native Air Interface. The 6G city-scale digital twin is aimed at transforming the way we envisage wireless networking and its many components.

In 2022, the company revealed its support for critical, collaborative research at the Institute for Wireless Internet of Things and the Open6G cooperative research centre at Northeastern University. This was part of the 6G Forward Program, with a primary objective of creating a digital twin of a 6G network using large-scale RF propagation channel modelling, utilising AI and machine learning technologies.

Recent advancements include the augmentation of ray tracing for RF propagation modelling using AI/ML, conducting real-world measurement campaigns in the Northeastern Boston campus using VIAVI's Ranger, a rugged RF capture and playback instrument, and incorporating higher-layer Key Performance Indicators (KPIs) in the digital twin to more effectively model the impacts of network conditions on application performance.

Dr. Ian Wong of VIAVI's CTO Office said, "Our research collaboration with Northeastern University has led to breakthroughs in the use of AI/ML for radio propagation modelling, [which is] critical in enabling large-scale network digital twins, which VIAVI is well poised to deliver given our leading network emulation solutions in the lab and network monitoring and optimization solutions in the field, gathering data from actual operator networks."

As part of this research, the Institute for the Wireless Internet of Things (WIoT) at Northeastern University has been leveraging VIAVI's cutting-edge testing and measurement equipment to model and deploy high-fidelity digital twins of real-world wireless networks on its Open RAN Digital Twinning platform, Colosseum. Professor Tommaso Melodia, Director of WIoT at Northeastern University, believes that this will facilitate the progress of AI-driven solutions for 5G and future network generations in a risk-free digital environment.

Along with the digital twin, VIAVI has introduced the AI-Native Air Interface (AI-AI), signalling a notable shift in traditional methods of developing, standardising, and commercialising communication technologies. By way of AI-AI, VIAVI aims to more effectively supply data to applications while addressing communication issues and hardware limitations. In the physical layer of wireless communications, conventional signal processing blocks are suggested to be replaced with trained AI models for the neural receiver concept.

VIAVI has developed and demonstrated its own receiver as part of a comprehensive test and training environment aimed to enable testing of these neural receivers. The company's base station employs an AI-aided constellation design, with the modulation block being replaced by a neural network to design the custom constellation for the receiver.

"VIAVI continues to explore and develop groundbreaking future generations of wireless technology, and we are at the frontier of AI-native 6G," expressed Dr. Stephen Wang, Managing Director of VIAVI's Marconi Labs. "Our 6G research helps the industry create networks that dynamically adapt to different environments and conditions. We look forward to working with research labs and network equipment manufacturers to accelerate development of these technologies."