Samsung Electronics and NTT DOCOMO Successfully Verify AI-RAN Based Communication Quality Optimization Technology

This page was machine-translated and may differ from the original. View original

Samsung Electronics and NTT DOCOMO Successfully Verify AI-RAN Based Communication Quality Optimization Technology

Published2026.08.10 12:01

Confirmed reduction in transmission speed degradation frequency from 13.1% to 7.2% in commercial network simulation

Samsung Electronics and Japan's mobile operator NTT DOCOMO have jointly developed and completed verification of AI-based Radio Access Network (AI-RAN) communication quality optimization technology. This technology works by having AI analyze individual users' movement patterns and real-time wireless network conditions to predict quality degradation in advance and automatically apply optimal network settings tailored to each user.

Samsung Electronics announced on the 10th that in simulation verification using data from NTT DOCOMO's Japanese commercial network and 5G test network conducted in January this year, the frequency of service transmission speed degradation occurrence decreased from 13.1% to 7.2%.

The existing base station operation method applied identical network settings to all connected terminals in bulk, repeatedly causing quality degradation issues such as connection drops in radio shadow areas.

The newly developed technology has AI learn users' movement paths and service usage history to identify signs of quality degradation in advance, and adjusts network settings such as frequency band selection before problems occur. A typical application example is AI detecting anticipated buffering during video streaming and automatically switching to optimal settings.

Expanding cooperation to include commercial network verification and joint 3GPP contribution

The two companies went beyond technology development and jointly performed all processes including securing Japanese commercial network drive test data and improving measurement procedures. They also jointly developed data processing procedures that reduce network load when operating AI-RAN.

The existing method involved bulk collection and processing of wireless environment information, creating heavy network burden, whereas the new process selectively processes only necessary information according to circumstances. The two companies jointly submitted this data processing procedure to the 3GPP (3rd Generation Partnership Project), the global mobile communications standardization body, in February this year, and continue cooperation on 6G standardization.

Jung Jin-kook, Senior Vice President and Head of Next-Generation Communications Research Center at Samsung Research (Samsung Electronics), stated, "This verification demonstrates that AI can practically improve individual users' service experience," and added, "We will continue technological advancement and standardization cooperation on AI-RAN technology with NTT DOCOMO to lead future user-centric communication technology."

Masafumi Masuda, 6G Technology Department Head at NTT DOCOMO, added, "We will enhance AI-based technology and service quality to deliver new value to our customers."

#5G #머신러닝 #삼성전자 #AI-RAN #무선접속망 #통신품질최적화 #6G표준화 #NTT DOCOMO #네트워크최적화

본 기사에 대한 정정·반론·추후보도 청구는 보도 청구 안내를, 그간 게재된 보도문은 정정·반론보도 모아보기를 참고해 주세요.

배종인 기자

All articles by this reporter

관련뉴스

The Problem with AI is Not Performance, but Trust

CEO Kang Min-seung emphasized at Snowflake's World Tour Seoul that generative AI has entered a phase where "trust" rather than accuracy becomes the key competitive advantage. As AI is applied to various tasks including consultation, risk management, and operational automation, incorrect data, erroneous responses, and bias are creating actual business risks. He pointed out that enterprises must build a trust layer above AI. To achieve this, accurate data management, semantic structuring, governance, and prompt security are essential. He explained that AI is not merely an automation tool but a technology that reorganizes the entire organization's workflows and decision-making systems. Snowflake provides a platform that supports this trust-based AI operation, emphasizing that enterprises should build "trustworthy AI" rather than "intelligent AI."

2026.08.28by 배종인 기자

The Decisive Factor for AI Agents in Finance: "Trustworthy Data Infrastructure"

The key to spreading AI agents in the financial sector is establishing a trustworthy data system. KB Kookmin Bank is operating over 100 AI agents by 2025 and is promoting expansion to 300. AI is automating repetitive tasks across various areas such as consultation, risk management, wealth management, and relationship management. However, if data quality, governance, and semantic structuring are insufficient, errors and risks increase. KB is building an AI-Ready organization through a multi-model strategy of GPT, Gemini, and Claude, as well as a Snowflake-based data system. The bank emphasized that AI has entered a phase where it restructures not just simple automation but the entire work process and decision-making system.

2026.08.28by 배종인 기자

Snowflake Presents Data Platform Roadmap for Agentic AI Era

Snowflake emphasized at the Seoul roundtable that the key to enterprise AI proliferation lies in "Agentic AI" and the integration of data and workflows. Bala Kasivisvanathan stated that AI is evolving beyond simple analytics to become the driver of task automation and operational optimization, and that organizations must strengthen their data quality, processes, and governance as prerequisites for this. CJ OliveNetworks introduced that it is currently expanding AI applications in logistics and operational automation. Snowflake stressed that companies need a strategic shift to connect AI adoption to tangible business impact.

2026.08.28by 배종인 기자

"All office workers will become agent managers"

At the Dell Technologies Forum 2026, Matt Dunfee, Senior Vice President at Dell Technologies headquarters, forecast that in the AI era, every worker will take on the role of managing dozens to thousands of agents, and emphasized that rather than simply adding AI to existing tasks, processes themselves must be redesigned. He pointed out that the success or failure of AI adoption depends not on technology itself, but on cost efficiency, data preparation, and AI economics, prototyping, and change management.

2026.08.28by 배종인 기자

Sang-Mo Yu, Dell President: "AI Is Now Infrastructure—Integrated Approach to Security, Power, and Data Centers Is Essential"

At Dell Technologies Forum 2026, Sang-Mo Yu, President of Dell Technologies Korea, emphasized that AI has transcended the role of a productivity tool to become core infrastructure for enterprises and everyday life, underscoring the necessity of a hybrid AI infrastructure strategy integrating power, cooling, security, and data centers. He disclosed that he utilizes more than 20 AI agents daily and identified embedded security and the absence of unified roadmaps as major challenges for enterprises.

2026.08.28by 배종인 기자