Keysight, Samsung Demonstrate End-to-End AI-RAN Validation Workflow with NVIDIA

Estimated reading time: 2 minutes

Keysight Technologies, Inc. and Samsung Electronics are collaborating to demonstrate an end-to-end Artificial Intelligence Radio Access Network (AI-RAN) testing and validation workflow with NVIDIA at Mobile World Congress 2026 in Barcelona. The demonstration shows how Keysight’s AI-RAN solution streamlines the validation of AI-driven RAN modules using the Physical Uplink Shared Channel (PUSCH) channel estimation use case, bringing data generation, artificial intelligence/machine learning (AI/ML) training, and performance benchmarking into a single automated workflow to accelerate innovation and reduce deployment risk for operators and vendors.

As AI moves deeper into the RAN, engineers must validate algorithms across diverse real-world network conditions. Data collection, model training, and performance benchmarking often occur in separate environments, making results difficult to compare, reproduce, and trust prior to deployment, particularly for physical-layer functions such as channel estimation that directly impact throughput, reliability, and user experience.

To address this, Keysight AI-RAN Simulation Toolset orchestrates an integrated, end‑to‑end workflow that automates realistic dataset and scenario generation, AI/ML model training, and repeatable benchmarking, enabling engineers to compare approaches consistently and gain clear performance insights before field testing. At MWC, this workflow is implemented end-to-end using partner compute and radio platforms to validate AI-driven RAN behavior in a realistic, controlled environment.

The demonstration integrates Keysight’s AI RAN Simulation Toolset with the NVIDIA Aerial Testbed, an end-to-end, over-the-air AI-RAN research testbed running on platforms including NVIDIA GH200 and NVIDIA DGX Spark, the NVIDIA Aerial Omniverse Digital Twin (a network digital twin) along with commercial radio hardware such as Analog Devices’ Titan O-RU platform. AI/ML models were developed by Samsung, NVIDIA, and Keysight, and are trained and benchmarked within a unified test workflow to deliver actionable performance insights.

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.”