AI-RAN test med brug af digitale tvillinger
I forbindelse med MWC 2026 i Barcelona vil Rohde & Schwarz i samarbejde med NVIDIA præsentere de seneste fremskridt inden for AI-RAN test med brug af digitale tvillinger (in english).
Rohde & Schwarz will showcase a new milestone in AI-driven wireless system testing at MWC Barcelona. The testbed, developed in collaboration with NVIDIA, integrates hardware-in-the-loop site-specific channel emulation using the NVIDIA Sionna Research Kit, enabling testing of AI-RAN applications under realistic channel conditions.
The demonstration highlights the long-term collaboration of Rohde & Schwarz and NVIDIA, focusing on prototyping and validation of AI-RAN innovation with cutting-edge test and measurement solutions.
Evolving from prior proof-of-concepts in advanced neural receiver design – including custom constellations for pilotless communication – the new testbed advances from link-level validation to system-level verification using the full 5G NR protocol stack.
Powered by a single NVIDIA DGX Spark, the NVIDIA Sionna Research Kit runs a software-defined 5G RAN based on OpenAirInterface, while supporting AI inference workloads that comply with the strict real-time constraints of wireless systems.
To showcase the flexibility of the research platform, a novel AI/ML-enhanced link adaptation algorithm has been integrated into the end-to-end system. It dynamically adjusts the downlink modulation and coding scheme (MCS) to optimize spectral efficiency and link reliability.
The AI-driven link adaptation can learn not only site-specific propagation characteristics but also user equipment-specific behavior on the fly, emphasizing the need for end-to-end testbeds that capture these effects.
The testbed integrates the R&S SMW200A vector signal generator featuring dynamic channel emulation capabilities and the FSW signal and spectrum analyzer. Jointly, these instruments enable the emulation of complex site-specific radio channels, seamlessly interfacing with the NVIDIA Sionna RT differentiable ray-tracing software. This closed-loop setup enables researchers and developers to evaluate the performance of novel AI-driven RAN features under dynamic, site-specific RF conditions – all without leaving the lab.
Gerald Tietscher, Vice President Signal Generators, Power Supplies and Meters at Rohde & Schwarz, says:
- We’re excited to continue our ongoing collaboration with NVIDIA with this latest proof-of-concept for testing AI-enhanced base stations for both 5G-Advanced and 6G under realistic propagation conditions. Leveraging digital twin technology and ray tracing, this approach aims to bridge the gap between AI-driven wireless simulations and real-world deployment, facilitating more efficient and accurate testing of next-generation receiver architectures.
Soma Velayutham, global industry business development lead for telecommunications at NVIDIA adds:
- Synthetic data generation is transforming the way we train and validate AI-RAN systems by ensuring accuracy, scalability, and privacy, especially in settings of sparse data. Rohde & Schwarz, leveraging the NVIDIA Sionna Research Kit, exemplifies how industry-leading expertise and innovative technology can come together to accelerate progress in this critical field.
Visitors to MWC Barcelona 2026 can experience the hardware-in-the-loop validation of novel AI-RAN features live and speak with experts from Rohde & Schwarz and NVIDIA at the Rohde & Schwarz booth 5A80 in hall 5 from March 2 to 5, 2026.
For more information on AI/ML for 6G networks:
www.rohde-schwarz.com/6G-AI-ML
