Keysight, Samsung, and NVIDIA Collaborate to Advance AI-Optimized RAN Technology for 5G and Beyond

Collaboration for AI-Enhanced RAN Technology

Keysight Technologies, Samsung, and NVIDIA have announced a groundbreaking collaboration to develop artificial intelligence (AI) models aimed at improving radio access network (RAN) performance for 5G-Advanced and 6G technologies 1

1

2

2

. This initiative, developed under the AI-RAN Alliance, addresses key challenges in traditional RAN systems and promises significant advancements in telecommunications infrastructure.

AI Model Development and Implementation

The collaboration has resulted in the successful generation of advanced AI models for channel estimation in the uplink receiver. These models have demonstrated remarkable improvements in lab environments, including a 30% increase in cell edge throughput compared to conventional static rules-based approaches 1

1

3

3

. The AI models are designed to enhance system capacity, improve network efficiency, and deliver superior user experiences.

Samsung will integrate these powerful AI models into their virtual RAN (vRAN) software solution, which will be showcased at the Mobile World Congress (MWC) 2025 in Barcelona 2

2

. The implementation utilizes Samsung's radio point and a distributed unit (DU) based on the NVIDIA AI Aerial platform, running on the NVIDIA GH200 Grace Hopper Superchip platform 1

1

.

Technology and Performance Enhancements

Keysight's Channel Emulation Solutions have played a crucial role in providing channel generation capabilities for various conditions, along with real-time signal processing and radio frequency (RF) capabilities 1

1

. The AI-based approach enables:

1. Precise channel estimation
2. Optimized resource allocation
3. Reduced power consumption

These advancements are particularly significant for addressing uplink performance concerns in commercial 5G deployments, especially at cell edges where limited user equipment (UE) transmission power affects the base station's received signal-to-noise ratio (SNR) 1

1

.

Industry Impact and Future Prospects

The collaboration is expected to drive innovation and accelerate the global adoption of AI-enhanced RAN technologies 2

2

. Charlie Zhang, Senior Vice President at Samsung Research, emphasized the importance of this milestone in evolving toward AI-native and sustainable telecommunication networks 1

1

2

2

.

Soma Velayutham, Vice President of Telecoms at NVIDIA, highlighted the flexibility and efficiency gains unlocked by AI in radio signal processing pipelines 1

1

3

3

. Giampaolo Tardioli, Vice President of 6G and Next Generation Technology at Keysight, underscored the transformative potential of AI-native networks resulting from this partnership 1

1

3

3

.

Broader Industry Developments

This collaboration aligns with other significant developments in the telecommunications industry. For instance, Jio Platforms Limited (JPL), along with AMD, Cisco, and Nokia, has announced plans to develop an Open Telecom AI Platform, offering a 'multi-domain intelligence' framework to introduce AI and automation to various layers of network operations 2

2

.

As the industry moves towards more advanced and efficient network technologies, collaborations like the one between Keysight, Samsung, and NVIDIA are paving the way for the next generation of telecommunication networks that are both AI-native and sustainable.