SoftBank and Ericsson just pulled off a live 5G AI scheduler test in Japan — no lab, just real-world network action — proving AI can boost spectral efficiency by 25% and user throughput by up to 50% in key spots, with 10% average gains across the board. This isn’t just tinkering; it’s the first validation of an “AI-native RAN” approach, where machine learning runs directly on baseband gear to adapt in real time, helping edge users and noisy areas stay connected without new hardware. As AI apps explode and traffic surges, they’re betting AI embedded in the network is the smarter, more efficient future — not just more towers.
Listen in comfort: Get a discount on a Soli Pillow: http://solipillow.com/discount/dnn.
Advertise on DNN: advertise@thednn.ai
This is an automated, high-level news summary based on public reporting. Report issues to feedback@thednn.ai.
Podden och tillhörande omslagsbild på den här sidan tillhör
The Daily News Now!. Innehållet i podden är skapat av The Daily News Now! och inte av,
eller tillsammans med, Poddtoppen.
