Keysight, Samsung and NVIDIA Showcase Unified AI-RAN Validation at MWC 2026

At Mobile World Congress 2026 in Barcelona, Keysight Technologies, Inc. joined forces with Samsung Electronics and NVIDIA to unveil a powerful end-to-end Artificial Intelligence Radio Access Network (AI-RAN) testing and validation workflow. Through this live demonstration, the companies highlighted how operators and vendors can accelerate AI-driven RAN innovation while simultaneously reducing deployment risks.

Notably, the collaboration centers on streamlining the validation of AI-powered RAN modules using the Physical Uplink Shared Channel (PUSCH) channel estimation use case. By bringing data generation, artificial intelligence and machine learning (AI/ML) training, and performance benchmarking into a unified automated workflow, the solution eliminates the fragmentation that often slows development cycles.

Read More: The Autonomous Enterprise Question: How Much Control Should We Hand to AI Agents?

As AI technologies increasingly integrate into the radio access network, engineers must validate advanced algorithms across a wide range of real-world network scenarios. However, in many cases, data collection, model training, and benchmarking occur in separate environments. Consequently, this fragmented approach makes it difficult to compare results, reproduce findings, and confidently validate performance before deployment especially for physical-layer functions like channel estimation that directly influence throughput, reliability, and overall user experience.

To solve this challenge, Keysight introduced its AI-RAN Simulation Toolset, which orchestrates a comprehensive, end-to-end workflow. Specifically, the platform automates realistic dataset and scenario generation, supports AI/ML model training, and delivers repeatable benchmarking capabilities. As a result, engineers can consistently evaluate different approaches and gain actionable performance insights prior to field testing.

At MWC 2026, the companies implemented this integrated workflow using partner compute and radio platforms to validate AI-driven RAN behavior within a realistic yet controlled environment. The demonstration combined Keysight’s AI-RAN Simulation Toolset with the NVIDIA Aerial Testbed an over-the-air AI-RAN research platform powered by NVIDIA GH200 and NVIDIA DGX Spark systems. Additionally, the setup incorporated the NVIDIA Aerial Omniverse Digital Twin, a network digital twin environment, alongside commercial radio hardware such as Analog Devices’ Titan O-RU platform.

Furthermore, Samsung, NVIDIA, and Keysight collaboratively developed the AI/ML models used in the demonstration. The unified workflow trained and benchmarked these models to deliver measurable, performance-based insights.

Read More: How Domain-Specific Language Models Are Trained: Data, Fine-Tuning, and Governance

Soma Velayutham, Vice President, AI & Telecoms, NVIDIA, said: “As AI moves deeper into the radio access network, validating complex algorithms across diverse, real-world conditions becomes even more critical. By leveraging NVIDIA AI Aerial platforms into a unified workflow, Keysight is simplifying the end-to-end data pipeline, essential for training, validating, and deploying AI-native 5G and 6G networks.”

Charlie Zhang, Executive Vice President, Samsung Research America, said: “Our partnership with Keysight and NVIDIA is revolutionizing network deployment by delivering integrated AI-RAN validation, bridging the gap between theoretical models and real-world implementation. This collaboration empowers the industry to confidently adopt AI-driven RAN solutions, ensuring robust and commercially viable foundations for the future of 6G networks.”

Balaji Raghothaman, Chief Technologist-6G, Keysight, said: “AI in the RAN only delivers value when it can be validated with confidence. Working with NVIDIA and Samsung, we’re demonstrating a streamlined, automated workflow that unifies data generation, AI/ML training, and benchmarking, helping operators and vendors accelerate deployment, reduce risk, and make more informed decisions as they introduce AI-driven RAN capabilities.”

Ultimately, this collaboration marks a significant step toward commercially viable AI-native 5G and 6G networks, providing the telecom ecosystem with the tools needed to validate, deploy, and scale AI-powered RAN technologies with confidence.

Write to us [⁠wasim.a@demandmediaagency.com] to learn more about our exclusive editorial packages and programmes.