Samsung Electronics and KDDI have completed a joint trial of Samsung’s AI-powered RAN Speed Optimizer (RSO) on KDDI’s commercial 5G Standalone network in Japan.
The trial began in late 2025 and ran for several months in and around Tokyo, covering dense urban, suburban, and rural areas. It utilized 100 MHz of 3.7 GHz TDD spectrum across hundreds of cells. Samsung’s RSO delivered an average 31% increase in 5G downlink throughput during peak hours across the trial area, with a maximum increase of 52% in dense urban locations.
The AI solution performs parameter optimization on a per-cell basis, moving beyond conventional cluster-level settings that apply uniform parameters across multiple cells. RSO employs an AI-based prediction model that automatically analyzes site environment data and recommends optimized parameters for each individual cell. It forms part of the Samsung CognitiV Network Operations Suite (NOS).
The trial tested AI model training under diverse real-world traffic and network conditions. It demonstrated automatic adjustment to changing network scenarios, with potential for reduced manual intervention.
Kazuhiro Furuhata, Chief Network Officer at KDDI, stated: “Combining KDDI’s accumulated expertise in network innovation and Samsung’s technical leadership, this field trial proves that individual tuning for cells a long-standing industry challenge has now become a reality through the integration of AI.”
June Moon, Executive Vice President, Head of R&D, Networks Business at Samsung Electronics, said: “Samsung continues to help operators like KDDI build intelligent and efficient networks by weaving in AI-powered innovation. Since 2024, we have been actively testing and training our AI-powered RSO technology in the field... This trial with KDDI exemplified how Samsung’s AI-powered innovation can bring advanced optimization to live commercial networks.”
Samsung and KDDI plan to continue evaluating AI-based optimization technologies for broader commercial network applications. The companies have a long-standing collaboration on fully virtualized network deployments.
