Engineers from the two companies spent the best part of a year creating a deep learning-based system that can automatically recommend optimal parameters for base station environments.
Subscribe today for free
“This is a meaningful achievement that has confirmed that the potential performance of individual base stations can be maximised by incorporating AI,” said Ryu Tak-ki, head of the infrastructure technology division at SK Telecom. [translated]
Dubbed the AI-RAN Parameter Recommender, the jointly developed system can be applied to commercial networks, with the pair testing it out on SK’s own infrastructure.
Mobile base stations experience varying wireless conditions depending on their location and nearby facilities. As a result, the quality of 5G services can differ significantly across areas, even when using the same standard equipment.
SK Telecom turned to AI to enhance 5G network operations, applying a deep learning model to analyse the relationship between wireless network data and AI parameters. The approach enables predictions of varying wireless environments and service characteristics, automatically deriving optimal settings to boost perceived quality.
Samsung then added its Network Parameter Optimisation AI Model to improve wireless network environment and performance enhancement.
With the two solutions combined, the jointly developed AI solution can predict wireless environments and automatically set optimal parameters for each base station environment, enhancing 5G service quality and adaptability across diverse locations.
“AI is a key technology for innovation in various industrial fields, and it is also playing a decisive role in the evolution to next-generation networks,” said Choi Sung-hyun, head of the advanced development team in Samsung Electronics’ network business division. “Samsung Electronics will continue to take the lead in developing intelligent and automated technologies for AI-based next-generation networks.” [translated]
Beyond tests with Samsung, SK Telecom is advancing AI to transform its network, including technologies that automatically adjust base station output and apply future beamforming, which directs antenna signals toward specific devices for stronger transmission and reception.
“We will accelerate the evolution into an AI-Native Network that provides differentiated customer experiences through the convergence of telecommunications and AI technologies,” Ryu added. [translated]
RELATED STORIES
SK Telecom enhances AI capabilities with Lambda partnership
Samsung and NTT Docomo team up to research AI-powered 6G technology
