Leading Tokyo-based multinational SoftBank has announced that it has called upon Ericsson’s machine learning capabilities to aid the design and development of its advanced radio network in Tokai, Japan.
SoftBank utilised Ericsson’s service offering to group cells in clusters, taking data from these cells using machine learning techniques, whereby the firm was then able to reduce the network’s operational expenditure whilst also improving performance, cutting the lead time by 40%.
“We applied Ericsson's service on dense urban clusters with multi-band complexity in the Tokai region,” said Ryo Manda, Radio Technology Section Manager at the Tokai Network Technology Department of SoftBank. “The positive outcome exceeded our expectations and we are currently proceeding in other geographical areas with the same method and close cooperation with Ericsson.”
The process of doing this has been cited by Ericsson as being a “highly complex task” and a “tremendous challenge”. However, the success of the service allowed Softbank to automate its regional radio access network design.
“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, Ericsson. “It is very exciting to see that the new methods have been successfully applied in SoftBank's network.”
In the aim of furthering the application and usage of machine learning within the telecommunications industry, Ericsson is looking to develop use cases at its Artificial Intelligence Lab, hosted in both Japan and Sweden.