With promising results for 5G and 6G networks, Keysight, Samsung, and NVIDIA unveil an AI-driven model to boost RAN performance, improving throughput and power efficiency.
Keysight Technologies, Samsung, and NVIDIA have recently jointly developed an AI model to improve radio access network (RAN) performance, particularly for 5G-Advanced and 6G technologies.
The new model focuses on enhancing throughput, increasing system capacity, and reducing power consumption, with plans for global deployment of the AI-optimised software. It was demonstrated at the Mobile World Congress 2025 last week in Barcelona.
In a press release, Keysight noted that a major concern in 5G networks is uplink performance, particularly at the cell edge, where lower user equipment transmission power reduces the base station’s received signal-to-noise ratio (SNR). Conventional algorithms struggle in these conditions, making AI a potential solution.
This model addresses these challenges in traditional RAN systems, such as high latency and limited throughput.
Furthermore, AI-driven channel estimation and resource optimisation could help overcome these challenges by improving efficiency and power management. Keysight’s channel emulation solutions were used to test the AI model’s capabilities, offering real-time signal processing and RF generation.
Meanwhile, in laboratory experiments, the AI model achieved a 30 per cent improvement in cell edge throughput compared to traditional static approaches. The model was evaluated using an end-to-end setup involving Samsung’s radio point and distributed unit, supported by the NVIDIA GH200 Grace Hopper Superchip and AI Aerial platform.
“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,” said Charlie Zhang, Senior Vice President at Samsung Research.
Expressing enthusiasm about the model, Soma Velayutham, Vice President, Telecoms at NVIDIA, said: “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.”
“This partnership not only enhances performance and reduces power consumption but also paves the way for more energy-efficient networks,” noted Giampaolo Tardioli, Vice President, 6G and Next Generation Technology at Keysight.
As the industry looks to future technologies like 6G, such innovations could become critical for improving the efficiency and effectiveness of mobile networks.
