Dropped connections on high-speed trains reduced by about 29%

KT said on November 5 that it had developed a wireless network optimization technology with Samsung Electronics to reduce dropped connections on high-speed trains.


KT employees are testing technology designed to reduce degradation in communications quality along a high-speed rail line in Pyeongtaek, Gyeonggi Province. Provided by KT.

KT employees are testing technology designed to reduce degradation in communications quality along a high-speed rail line in Pyeongtaek, Gyeonggi Province. Provided by KT.

View original image

On high-speed trains traveling at 250 km/h or faster, frequent handovers between base stations can delay data transmission or reduce call quality. The two companies use artificial intelligence (AI) to identify sections where communications quality repeatedly deteriorates and patterns in network connections, then adjust and optimize the timing of handovers between base stations.


The technology was tested on a section of the Gyeongbu Line between Godeok-myeon in Pyeongtaek and Maesong-myeon in Hwaseong. After the technology was applied, the rate of dropped connections while traveling on the high-speed train fell by about 29%. In other words, if the number of dropped connections had been 100, the technology would have reduced it to about 71.


KT plans to consider applying the technology in actual high-speed rail sections and continue its technical cooperation with Samsung Electronics in the field of AI Radio Access Network (AI-RAN).



Lee Jong-sik, head of KT's Future Network Lab in the Network Division and an executive vice president, said, "This test was a meaningful achievement, confirming the potential to improve the quality customers experience in areas with weak service, such as high-speed rail lines, using AI. We will continue to develop AI-RAN technology to improve the quality our customers experience."


This content was produced with the assistance of AI translation services.

© The Asia Business Daily. All rights reserved. Unauthorized AI training and use prohibited.

Today’s Briefing