Ericsson wins AI RAN contract with Japan’s NTT Docomo

Published: 17 March 2020 - 1:13 p.m.

Ericsson to supply Artificial Intelligence (AI) Performance Diagnostic solutions for NTT Docomo’s mobile network

Ericsson has won a contract to supply Artificial Intelligence (AI) based optimisation solutions for NTT Docomo’s Radio Access Network.

The announcement builds on over a decade of collaboration between the two companies, which has recently focused on 5G proof of concept activities.

The AI-based Performance Diagnostic solution for RAN optimisation is one such effort and result of this collaboration.

“NTT DOCOMO has proactively worked on service area expansion and communication quality improvement in an effort to provide comfortable communication areas to our customers. Leveraging AI and our know-how that has been developed for years, we will further improve network quality,” said Hozumi Tamura, executive vice president, NTT Docomo.

The AI-based Performance Diagnostic solution will apply innovative machine learning and complex problem-solving techniques to classify cell performance issues and recommend changes in the Radio Access Network. NTT DOCOMO’s planning and optimisation teams will be able to evaluate the solution’s output to expedite optimisation efforts accurately and in a timely manner.

The companies conducted trials in 12 cities. The Ericsson Performance Diagnostics solution achieved 98 per cent accuracy in classifying performance issues. The commercial operation to cover nationwide network is planned for March 2020.

“Close collaboration with NTT DOCOMO highlights the real benefits and value that AI-based and machine leaning solutions can bring to communications service providers’ network operations. This solution maximises end-user experience in service provider’s networks while minimising their total cost of ownership,” said Peter Laurin, executive vice president and head of business area managed service at Ericsson.

Click here to add your comment

Please add your comment below
Your email address will not be published