Keysight Technologies Partners with Samsung and NVIDIA to Revolutionize AI-for-RAN Technology

Traditional RAN systems face a multitude of challenges that hinder their performance, including limited throughput, high latency, and inefficient resource utilization. These issues are particularly pronounced in commercial 5G deployments, where uplink performance at the cell edge is a significant concern. The limitations of user equipment (UE) transmission power can adversely impact the base station's received signal-to-noise ratio (SNR), complicating the channel estimation process.

The introduction of AI modeling provides a revolutionary approach to these challenges, enabling precise channel estimation and optimized resource allocation. This innovation not only enhances system capacity but also improves overall network efficiency, ultimately delivering superior user experiences.

Keysight's Channel Emulation Solutions play a vital role in this collaboration, offering advanced channel generation capabilities under various conditions. These solutions facilitate real-time signal processing and radio frequency (RF) functionalities. Through the partnership, Samsung has successfully generated advanced AI models for channel estimation in the uplink receiver, achieving remarkable improvements in lab settings.

Notably, simulated experiments demonstrated a 30% increase in cell edge throughput when utilizing the AI model for channel estimation as opposed to traditional static, rules-based approaches. The performance evaluation of this innovative AI model was conducted using an end-to-end setup, incorporating Samsung's radio point and a distributed unit (DU) based on the NVIDIA AI Aerial platform. This setup was implemented on the NVIDIA GH200 Grace Hopper Superchip platform, alongside Keysight's Channel Emulation and Core Emulation Solutions.

The collaboration is positioned as a significant milestone in the telecommunications industry, with the potential to accelerate the adoption of AI-enhanced RAN technologies.

Charlie Zhang, Senior Vice President at Samsung Research, expressed enthusiasm about the collaboration, stating, “We are excited to realize these amazing performance benefits of AI-based channel estimation through close collaboration with Keysight, NVIDIA, and the AI-RAN Alliance. This is an important milestone for our industry, as we evolve toward a future of next-generation telecommunication networks that are AI-native and sustainable.”

Soma Velayutham, Vice President of Telecoms at NVIDIA, highlighted the flexibility that AI brings to the radio signal processing pipeline, stating, “With the power of AI, the radio signal processing pipeline can be much more flexible, unlocking significant performance and efficiency gains. Keysight’s AI-for-RAN innovation, in collaboration with Samsung and NVIDIA, is a significant step toward smarter, more reliable AI-native wireless networks.”

Giampaolo Tardioli, Vice President of 6G and Next Generation Technology at Keysight, emphasized the transformative potential of this partnership, noting, “Our collaboration with Samsung, NVIDIA, and AI-RAN Alliance underscores the transformative potential of AI-native networks. This partnership not only enhances performance and reduces power consumption but also paves the way for more energy-efficient networks.”

The fruits of this collaboration will be showcased at Keysight's booth during the Mobile World Congress 2025 (#5F41 Hall 5), where attendees will have the opportunity to witness firsthand the capabilities of the AI-driven technology developed through this strategic partnership.

The integration of AI in RAN technologies heralds a new era for telecommunications, promising to deliver not only enhanced performance but also a more sustainable and efficient network infrastructure. As industry leaders come together, the future of telecommunications looks increasingly promising, driven by innovation and collaboration.