Ericsson announced that Japanese operator SoftBank has implemented a new method for radio access network design from Ericsson based on machine intelligence.
The service groups cells in clusters and takes statistics from cell overlapping and potential to use carrier aggregation between cells into account, thus reducing operational expenditure and improving network performance. Compared to traditional network design methods, this cut the lead time by 40%, says Ryo Manda, radio technology section manager of the Tokai Network Technology Department at SoftBank.
“We applied Ericsson’s service on dense urban clusters with multi-band complexity in the Tokai region. The positive outcome exceeded our expectations and we are currently proceeding in other geographical areas with the same method and close cooperation with Ericsson,” Manda said.
The foundation for the method is a thorough analysis of the actual radio network environment, for example taking cell coverage overlap, signal strength and receive diversity into consideration. The high number of possible relations between cells as well as considerations for network evolution, calls for substantial computational power and state-of-the-art machine learning techniques.
This complex task was a tremendous challenge that Ericsson solved by implementing a design concept based on network graph machine learning algorithm (community detection) that the vendor has now patented.
SoftBank applied big data analytics to a cluster of 2,000 radio cells, and data was analyzed for optimal configuration.
“There is a huge potential for machine learning in the telecom industry and we have made significant investments in this technology,” said Peter Laurin, head of managed services at Ericsson. “There is a strong demand for this type of solutions and deployments of this service to other Tier-1 operators in other regions are ongoing.”