The trial was run in London using machine learning and other kinds of AI to automatically achieve the balance between energy savings and performance
Vodafone UK and Ericsson have successfully reduced daily power consumption of 5G Radio Units by up to 33% daily in trial sites across London. Ericsson’s Service Continuity AI App suite with Intelligent Energy Efficiency dynamically manages power consumption in the RAN, based on live traffic data.
The trail combined machine learning and other kinds of AI to save energy without affecting performance.
As part of the trial, Vodafone UK implemented three use cases which work in tandem to measure, predict and optimise energy consumption across the network.
Here’s what each of the three use cases do:
- 5G Deep Sleep uses predictive algorithms to put radios into a hibernation state, cutting energy consumption by up to 70% during off peak hours.
- 4G Cell Sleep Mode Orchestration creates a behavioural model of network cells to automatically balance energy savings and performance.
- A Radio Power Efficiency Map shows all the network cells, using machine learning to identify and rank underperforming sites for targeted improvements.
Andrea Donà, Chief Network Officer & Network Director, Vodafone UK, said, “We’re able to significantly improve energy efficiency without impacting the service our customers receive. Reducing power consumption at our trial sites is a big win, both financially and environmentally, and shows we can continue to improve the efficiency of our network as we build 5G coverage across the UK.”
Katherine Ainley, CEO of Ericsson UK and Ireland, said, “It’s exciting to see how our work with Vodafone UK is making a real difference. Our ability to…reduce network energy consumption while maintaining high performance standards is a testament to the innovation and expertise of our combined teams.”
