Ericsson has created a machine learning based product to help SoftBank’s radio access network design in Japan.

The product, which Ericsson sells as a service, improves radio access network design by grouping cells in clusters and taking data from these cells. Employing machine learning on these datasets, it looks at cell overlapping and carrier aggregation between cells, which reduces operational expenditure and improves performance in the network.

According to Ericsson, the process was ‘highly complex’ and a ‘tremendous challenge.’ The firm designed a concept based on network graph machine learning algorithms, which it has now patented.

Given the need to analyse a number of factors within the network radio environment, including cell coverage overlap, signal strength and receive diversity, a significant amount of computing power was required, as well as advanced machine learning techniques, in order to achieve the necessary results.

SoftBank has now automated the processes for radio access network design in a cluster of 2000 radio cells. Ryo Manda, Radio Technology Section Manager at the Tokai Network Technology Department of SoftBank, was pleased with the results. “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.”

Peter Laurin, Head of Managed Services at Ericsson, commented on the impact that machine learning can have on the telecoms industry. “There is a huge potential for machine learning in the telecom industry and we have made significant investments in this technology.

“It is very exciting to see that the new methods have been successfully applied in SoftBank’s network. There is a strong demand for this type of solutions and deployments of this service to other tier-one operators in other regions are ongoing.”

Ericsson provides managed services in three areas: networks, IT and network design & optimization. According to the company, it tries to help its clients meet ‘ever-changing demands from consumers and business users.’

SoftBank is the fourth largest business in Japan and is known for its wide investment portfolio, including its stake in the two largest ride-hailing companies in the world, Uber and Didi.