Rohde & Schwarz successfully validates ML-enhanced channel-state information feedback with Qualcomm for 5G-Advanced
In the evolving 5G landscape, channel-state
information (CSI) is essential for optimizing network performance and user
capacity. CSI enables efficient channel-dependent scheduling and adaptive
modulation, ensuring robust high-speed communications between base station and
mobile device. AI/ML driven CSI enhancements promise even greater efficiency,
reduced overhead, and improved user experience in 5G-Advanced and future 6G
networks. However, implementation across vendors will be challenging. Rohde
& Schwarz and Qualcomm Technologies have achieved an industry milestone by
demonstrating cross-vendor interoperability of ML-based CSI feedback
enhancements, to be showcased at MWC 2025 in Barcelona.
Caption: The CMX500 one-box tester supports
flexible ML model integration through the Open Neural Network eXchange (ONNX)
format.
Rohde & Schwarz today announced the
successful validation of machine learning-based channel-state information
feedback compression for 5G-Advanced networks with support from Qualcomm
Technologies, Inc., demonstrating a significant increase in throughput compared
to conventional methods. This breakthrough confirms the feasibility of
cross-vendor AI implementation in wireless communications with the aim of
enhancing network performance.
The two companies achieved interoperability
between ML models running on a mobile form factor reference design powered by a
Qualcomm® 5G Modem-RF and the CMX500 5G one-box signaling tester from Rohde
& Schwarz, implementing enhanced CSI feedback mechanisms studied in 3GPP
Release 18 and 19. The setup enables efficient compression of the channel state
based on CSI reference signal (CSI-RS) measurements, optimizing massive MIMO
operations critical for 5G networks. This validation demonstrated that the
throughput performance improved by 51% compared to Type I feedback followed by
wideband precoding, as defined in 3GPP Release 15.
Both parties employed separate training
approaches for AI models on the network and device side. Compatibility was
achieved through specified reference models. Utilizing autoencoder
architecture, Qualcomm Technologies implemented a proprietary device encoder,
while Rohde & Schwarz developed a decoder for its network emulator. The
CMX500 one-box tester supports flexible ML model integration through the Open
Neural Network eXchange (ONNX) format, enabling users to implement and validate
their own AI architectures for wireless testing scenarios.
Cross-vendor interoperability as milestone
for future standardization
The successful interoperability proves that
two-sided ML-based air interface enhancements can be effectively implemented
and tested across equipment coming from different vendors. It is a significant
step toward implementing AI-enhanced wireless communications, providing a
framework for testing and verification essential for the commercial deployment
of 5G-Advanced features. It also serves as a crucial milestone for the upcoming
standardization for a future 6G standard, where AI is expected to be natively integrated
into the air interface design from the beginning. Hence, cross-vendor AI
interoperability will be an essential foundation for future wireless systems.
Christoph Pointner, Senior Vice President of
Mobile Radio Testers at Rohde & Schwarz, says: “The capability of our
CMX500 to implement and validate ML-based signal processing highlights the need
for evolving test and measurement alongside wireless innovation. Thanks to ONNX
support, customers can integrate their own ML architectures, making the CMX500
a versatile platform for AI-enhanced wireless testing. Validating
interoperability with Qualcomm Technologies’ encoder confirms our commitment to
establishing essential verification frameworks for AI-driven communications,
from 5G-Advanced to future 6G systems.”
John Smee, Senior Vice President,
Engineering, Qualcomm Technologies, Inc. adds, “In this new 5G Advanced era of
connectivity, and as we look toward 6G, AI is even more critical not just for
the best user experiences but also for network performance. The joint research
between Qualcomm Technologies and Rohde & Schwarz validates that AI-based
CSI will help ensure these performance enhancements.”
Rohde & Schwarz will present the CSI
feedback enhancements demonstration together with Qualcomm Technologies live at
Mobile World Congress 2025 at Fira Gran Via in Barcelona in hall 5, booth 5A80.
A video preview of the demonstration is available here: https://www.rohde-schwarz.com/_251220-1545553.html
For further information on Rohde &
Schwarz solutions for AI and ML in 6G networks, visit: www.rohde-schwarz.com/6G-AI-ML
Snapdragon and Qualcomm branded products are
products of Qualcomm Technologies, Inc. and/or its subsidiaries. Qualcomm and
Snapdragon are trademarks or registered trademarks of Qualcomm Incorporated.
Rohde & Schwarz Rohde & Schwarz is striving for a safer and connected
world with its Test & Measurement, Technology Systems and Networks &
Cybersecurity Divisions. For 90 years, the global technology group has pushed
technical boundaries with developments in cutting-edge technologies. The
company's leading-edge products and solutions empower industrial, regulatory
and government customers to attain technological and digital sovereignty. The
privately owned, Munich based company can act independently, long-term and
sustainably. Rohde & Schwarz generated net revenue of EUR 2.93 billion in
the 2023/2024 fiscal year (July to June). On June 30, 2024, Rohde & Schwarz
had around 14,400 employees worldwide.
R&S® is a registered trademark of Rohde
& Schwarz GmbH & Co. KG.
All press releases, including photos for
downloading, are available on the internet at www.press.rohde-schwarz.com