Samsung noted it has been advancing AI-RAN technologies that tailor radio configurations based on individual conditions
In sum – what to know:
AI cuts real-world connection failures – Samsung and KT saw significantly fewer disconnections after applying user-level AI-RAN configurations across a commercial network trial involving about 18,000 users.
User-specific tuning replaces static settings – AI learns mobility and usage patterns to predict potential service disruptions, proactively optimizing radio parameters for each individual device.
Milestone for 6G readiness – The successful commercial validation strengthens Samsung and KT’s position in developing AI-driven network capabilities seen as essential for future 6G performance demands.
Korean companies Samsung Electronics and KT Corporation have successfully validated AI-based radio access network (AI-RAN) optimization technology on KT’s commercial network, claiming the first time the system has been demonstrated at scale in a live environment.
The achievement follows earlier simulation testing completed in June and provides new evidence of how AI can improve user-level service quality across diverse real-world conditions.
Samsung noted it has been advancing AI-RAN technologies that tailor radio configurations based on individual conditions rather than applying the same network parameters to every device connected to a base station. Traditional uniform configuration approaches often struggle when users move through coverage gaps or travel at high speeds, creating the potential for connection instability or dropped links, the vendor said.
The AI-RAN optimization validated by Samsung and KT uses AI to automatically assign optimal configurations for each user. The system learns from recurring issues associated with a user’s mobility patterns and past disruptions, predicting where problems may occur and proactively preventing service degradation. This user-level intelligence is designed to reduce connectivity issues before they affect the experience.
During a field test in Seongnam, Gyeonggi Province, Samsung Research and KT’s Future Network Laboratory applied the technology to approximately 18,000 users across mixed environmental conditions. The teams focused first on users who had historically experienced repeated disruptions, developing individualized configurations based on detected patterns. When these settings were deployed on KT’s commercial network, connection failures dropped significantly for the most-impacted users — and service quality improved for other subscribers in the surrounding area.
Samsung and KT expect AI-RAN optimization to become increasingly important as the industry moves toward 6G, where data consumption will rise sharply and network reliability will need to hold steady under broader, more complex mobility scenarios.
The Korean companies plan to expand testing to additional commercial networks while accelerating research into 6G-enabling AI technologies.
“This is a major milestone that shows how AI can improve user experience on real-world commercial networks,” said JinGuk Jeong, executive vice president and head of the Advanced Communications Research Center, Samsung Research at Samsung Electronics. “Through close collaboration with KT, we will continue shaping and validating the next generation of AI-driven communication technologies,” he added.
“This achievement demonstrates that AI can transform network operations around users,” said Jong-Sik Lee, executive vice president and head of Future Network Laboratory at KT Corporation.
Samsung also highlighted that it will continue deepening work with operators globally as it advances AI-driven 6G research and development.
