Telenor, Ericsson tap AI to unlock network energy efficiencies

As the industry inches towards cloud-native, programmable networks, Telenor and Ericsson reckon the time is right to see how AI might make them more energy efficient.

Nick Wood

December 1, 2023

3 Min Read
telenor

The two of them have signed a three-year MoU under which they will research, develop and test AI/ML solutions in the hope of improving energy performance without compromising on network quality.

There are two areas of engagement.

The first centres on energy management and optimisation, focusing particularly on the RAN. This makes sense as 5G network densification will see operators deploy more and more sites – especially once the use of millimetre-wave (mmWave) spectrum becomes more widespread – in an effort to add capacity. Without some cleverness behind the scenes, this promises to place greater demand on the grid.

5G comes with various energy-saving features where certain components can be switched on and off as needed. And as networks migrate to the cloud, it unlocks the ability to intelligently automate more of these features, which is where AI/ML comes in.

The other area of engagement revolves around responsible AI development. So much of the discussion around AI at the moment is about making sure it doesn't yield any unintended negative outcomes that a commitment to ethical AI comes with the territory with these sorts of announcements.

"We expect this collaboration to break new ground when it comes to leveraging AI and automation to help address the complexity of 5G networks, drive energy efficiencies, improve customer experience – and make Telenor an AI-first company," said Ieva Martinkenaite, SVP and head of Telenor research & innovation.

Telenor and Ericsson have set their sights on achieving certain objectives under their MoU.

They plan to produce joint publications on advanced ML methods in mobile networks, covering topics such as energy optimisation in RAN and secure, explainable AI. They will also create teaching modules and related resources to drive the development of AI-native telecoms.

Telenor and Ericsson also plan to test AI/ML systems in a live test network, focusing on energy efficiency, anomaly detection, and spectrum sharing, in cooperation with early adopters and Telenor customers.

The two also help to validate AI-driven 5G use cases and business models.

"Together with Telenor, we want to build new knowledge in the area of AI/ML to improve network operations and energy efficiency management for both parties," said Rita Mokbel, head of global customer unit Telenor at Ericsson. "We also expect to benefit from the real time collaboration as we will act on workable innovations as soon as possible to the benefit of our customers."

Like most telcos, Telenor has made some net zero commitments, and this partnership might contribute to meeting them. By 2030, it wants to reduce greenhouse gas emissions from its global operations by 57 percent. To that end, it's aiming for net zero at its Nordic business, and a 50 percent reduction in Asia.

More attention is also being paid to tackling emissions in the supply chain – also known as Scope 3 – and for Telenor, this is where vendors like Ericsson play their part. The Swedish kit maker has a plan to become net zero in its own activities by 2030, and across its entire supply chain by 2040.

Efforts are already underway across the industry to produce eco-friendly infrastructure. This MoU between Telenor and Ericsson suggests that operating these networks efficiently and sustainably is becoming an increasingly prominent part of the conversation.

About the Author(s)

Nick Wood

Nick is a freelancer who has covered the global telecoms industry for more than 15 years. Areas of expertise include operator strategies; M&As; and emerging technologies, among others. As a freelancer, Nick has contributed news and features for many well-known industry publications. Before that, he wrote daily news and regular features as deputy editor of Total Telecom. He has a first-class honours degree in journalism from the University of Westminster.

You May Also Like