It’s Only Common Sense: Why Engineering Expertise Has Become the Ultimate Competitive Advantage
The Chemical Connection: When History Repeats Itself on Diversification
Punching Out: M&A Deals in North American PCB and EMS Sectors for the First Half of 2026
NTT DOCOMO, INC. and Samsung Electronics announced that they have successfully validated AI-based radio access network (AI-RAN) optimization technology at the user level. This advancement is expected to usher in an era where networks autonomously recognize user contexts and service requirements, delivering optimal communication environments. Moreover, this validation represents an important step toward realizing predictive network operations, especially as AI-driven network optimization becomes increasingly prevalent in the 6G network.
Traditionally, all user devices (smartphones) connected to a single cell (base station) were subjected to the same network configurations. This approach often led to service quality degradation, such as connection drops in areas with weak signals. With the growing demand for high-quality video, online gaming, and video conferencing, users increasingly require stable, uninterrupted connectivity at all times.
This newly developed AI-RAN optimization technology operates at the individual-user level rather than applying the same configuration across all users connected to a single cell. It automatically applies configurations tailored to real-time wireless conditions and the services being used. The AI 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 collected 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 with operation without the technology.
Using aggregated data from user devices (MDT*1), the system analyzes individual user contexts and movement trends to detect early signs of throughput*2 degradation before service quality declines. For instance, if a user is predicted to experience a reduction in transmission speed below the required threshold, leading to service disruptions such as buffering or reduced video quality, the system will automatically switch to the optimal configuration, e.g. frequency band, to meet service demands.
Instead of focusing on radio link failure prediction, the two companies adopted a customer-experience-driven approach aimed at supporting services such as uninterrupted video streaming. The validation demonstrated AI's potential to enable the network to proactively predict and mitigate service-quality degradation.
Additionally, DOCOMO and Samsung developed an efficient data collection process to minimize network burden during wireless network optimization. Unlike traditional methods that required bulk collection and processing of wireless environment data, the new procedure selectively gathers only necessary information based on specific user issues, reducing strain on the network while obtaining the critical data needed for AI-driven throughput degradation prediction and network optimization. In February, the companies contributed jointly to 3GPP discussions on data collection methods, further advancing 6G technology standardization efforts.
Moving forward, DOCOMO and Samsung will continue to advance this technology and explore future 6G use cases. The two companies also intend to contribute the AI-based throughput degradation prediction technology and efficient data collection technologies developed through this work to 3GPP discussions, taking a world-leading role in realizing of AI-Centric Networks in which networks autonomously learn, predict, and optimize their behavior through AI.
"This achievement represents a significant step toward realizing more adaptive and user-centric communication experiences in future networks. Through partnerships with Samsung, DOCOMO will continue to advance AI-based technologies and explore practical applications to further enhance service quality and deliver new value to our customers," said Masafumi Masuda, Senior Vice President and General Manager of the 6G-Tech Department, R&D Innovation Division, NTT DOCOMO.
"By shifting our research focus from overall cell performance to AI-driven individual user considerations, we have demonstrated the potential for enhanced perceived quality at the user level," said JinGuk Jeong, Executive Vice President and Head of the Advanced Communications Research Center, Samsung Research at Samsung Electronics. "Through close collaboration with DOCOMO, we will continue securing core technologies for future communications centered around users."
(1) Minimization of Drive Test is an automated process that anonymously collects communication quality information from user devices, such as smartphones, and applies insights to improve area coverage quality.
(2)The data transmission speed in communication, measured as the amount of data transferred per unit time, closely reflecting the actual communication speed experienced by users.
