Advancing AI-Driven Uplink Optimization and Life Cycle Management for RANs
Case Studies
MediaTek and Keysight developed a working prototype that advances AI-driven uplink optimization and model life cycle management for next-generation radio access networks. The prototype shows how AI-enabled, RAN-assisted intelligence can adapt to site conditions, improve uplink performance in real time, and remain effective through model retraining and over-the-air updates.
The prototype uses Keysight Channel Studio RaySim, Network Emulation solutions, and Channel Emulation solutions to create realistic, repeatable validation scenarios. The work supports AI-native RAN development by combining site-specific model retraining, RAN-assisted AI decision-making, and controlled testing that mimics real-world network conditions.
Keysight and MediaTek developed a working prototype that combines RAN-assisted AI decision-making, site-specific model retraining, and over-the-air model updates. The prototype was built in a controlled test environment that mimics real-world network conditions, allowing teams to evaluate AI-enhanced uplink performance under repeatable scenarios.
Keysight Channel Studio RaySim supports realistic RF channel modeling using 3D ray-tracing capabilities. In this collaboration, it helped generate high-fidelity real-world training datasets for AI-enhanced transmitter model development and validation. These datasets support the testing of device-level transmit diversity techniques across a range of modeled environments.