NTT DOCOMO, INC. and Samsung Electronics have announced the successful validation of AI-based radio access network (AI-RAN) optimization technology at the user level, marking a significant advancement in network autonomy. This development is poised to enable networks to autonomously recognize user contexts and service requirements, delivering optimal communication environments.
The validation represents a critical step toward predictive network operations, as AI-driven network optimization becomes more prevalent in the upcoming 6G network era. Traditionally, user devices connected to a single cell were subjected to uniform network configurations, often leading to service quality issues such as connection drops in areas with weak signals. The new AI-RAN optimization technology addresses these challenges by operating at the individual-user level, automatically applying configurations tailored to real-time wireless conditions and service demands.
The AI system learns each user's movement patterns and service usage behavior, predicting potential service quality degradation before it occurs. In a validation conducted in Japan in January 2026, using simulations based on data from DOCOMO's commercial network and a local 5G trial field, the companies reduced the frequency of communication-speed degradation from 13.1% to 7.2%, an improvement of 5.9 percentage points compared to operations without the technology.
By utilizing aggregated data from user devices, the system analyzes individual user contexts and movement trends to detect early signs of throughput degradation before service quality declines. For instance, if a user's transmission speed is predicted to fall below the required threshold, the system will automatically switch to the optimal configuration, such as a frequency band, to meet service demands.
Unlike traditional methods that required bulk data collection and processing, the new procedure selectively gathers only necessary information based on specific user issues, reducing network strain while obtaining critical data needed for AI-driven throughput degradation prediction and network optimization. In February, the companies contributed to 3GPP discussions on data collection methods, advancing 6G technology standardization efforts.
Moving forward, DOCOMO and Samsung plan to continue advancing this technology and exploring future 6G use cases. The two companies also intend to contribute the AI-based throughput degradation prediction technology and efficient data collection technologies to 3GPP discussions, aiming to play a leading role in realizing AI-centric networks where networks autonomously learn, predict, and optimize their behavior through AI.
Masafumi Masuda, Senior Vice President and General Manager of the 6G-Tech Department at NTT DOCOMO, highlighted the achievement as a significant step toward more adaptive and user-centric communication experiences. JinGuk Jeong, Executive Vice President and Head of the Advanced Communications Research Center at Samsung Electronics, emphasized the potential for enhanced perceived quality at the user level through AI-driven individual user considerations.
Comments are closed.