KITECH Webinar_~7.22
Physical AI HBM Smart Factory SDV AIoT Power Semicon 특수 가스 정정·반론보도 모음 e4ds plus

SKT Develops Wireless Network AI Quality Management Solution

Google 우선 소스 기사입력2023.03.28 15:10


'A-STAR' applied to nationwide base station management
Network quality monitoring and analysis of causes of quality degradation

SK Telecom is expected to be able to prevent wireless network quality degradation more intelligently by managing the quality of wireless networks with AI.

SK Telecom announced on the 28th that it has developed A-STAR (Access-Infra Service for Targeting & Action Recommendation), an AI solution for wireless network quality management, and applied it to its nationwide base stations.

'A-STAR' is a solution that continuously monitors the status of hundreds of thousands of base stations nationwide, identifies base stations expected to affect customer experience quality, reports these to field operation managers, and recommends causes of problems and improvement methods.

Based on this, A-STAR's functions include: △'wireless quality monitoring' which analyzes quality data of base station equipment nationwide every hour and reports abnormalities to the person in charge; △'quality deterioration cause analysis' which analyzes an average of about 250 types of quality data per equipment and selects and provides the core cause of the deterioration; and △'improvement plan recommendation' which recommends an appropriate improvement method through an AI algorithm that compares and learns data on quality deterioration situations with past quality improvement measures.

SKT compared the results with the existing method and analyzed the quality. The time required was reduced by 80.7%, and base stations were proactively improved by about 46.7%, it said.

A-STAR is the result of organic collaboration between network field experts from SKT and SK O&S. SKT began developing A-STAR in 2020, and through two years of development and field activity verification, as well as gradual supplementation and improvement of functions, it secured the practical usability of the AI model.

A-STAR receives the final actions taken by field quality improvement managers when the recommended results are inappropriate and retrains them. It is configured to continuously improve the performance of AI, so that it can provide more accurate information over time.

SKT is continuously improving A-STAR by shortening the quality analysis cycle of A-STAR and expanding the optimal movement route recommendation function to enhance the effectiveness of improvement activities by field staff.

Park Myeong-sun, SKT Infrastructure DT Manager, said, “SKT has further upgraded the intelligence of its network operations by utilizing AI technology in customer quality management activities,” and “We will continue to make changes in the field to further evolve with AI infrastructure in the future.”