Ericsson and Far EasTone’s model for sustainable network excellence
Learn how Service Continuity AI app suite supported a sustainable, healthy network and saved 25% energy in a collaboration with Far EasTone.
Executive summary
Find out how Ericsson’s Service Continuity AI app suite helped Taiwanese operator Far EasTone to make a 25 percent saving on their daily RAN energy consumption, with no adverse impact on network performance.
Using machine learning and artificial intelligence, the AI app suite examines and optimizes the network, reducing energy consumption and solving problems before they even occur.
Highlights
The solutions framework deployed in the collaboration are part of Ericsson’s cutting-edge Service Continuity AI app suite. These seek to solve issues in the network before they impact the network’s customer, using a range of advanced algorithms and AI tools to actively look for potential adjustments.
In Ericsson and FET’s collaboration a safety- first approach was initially adopted, and a more conservative level of energy savings was pursued. As the AI proved its ability over time, the level ambition was gradually increased to deliver better results. At first FET only used the energy-saving solution during off-peak night-time hours, but later on the operator decided the solution could be relied upon across a full day, including during busier periods.
"Sustainability is a top priority for Far EasTone. On top of that, Radio Access Network (RAN) stations and electricity consumption account for 71 percent of our electricity bill every year, regardless of savings in other network components – that's huge. Anything Ericsson can do to improve network energy efficiency is of major value therefore."
- Chee Ching, President FET
The challenge
The issue facing Far EasTone is one shared by every comunications service provider (CSP) around the globe – to maximize energy efficiency and minimize waste, without any negative impact on network performance.
That means being able to provide the energy needed at peak times, reducing it when demand is lower and ensuring that the network is optimized and functioning correctly so that nothing goes to waste.
- Balancing superior network performance with maximum energy efficiency
- Using artificial intelligence (AI) to dynamically respond to network energy needs
- Unlocking network performance insights from energy data
- Identifying and fixing energy issues automatically using AI and machine learning
- Creating a sustainable network template for the future
The solution
Ericsson’s Service Continuity AI App suite was deployed on the Far EasTone network, utilizing artificial intelligence and machine learning to respond dynamically to the network’s energy needs.
The app is a highly-complex AI solution that uses the network data to train itself, accurately predicting when network components can be closed down and woken up again without impacting network performance. Network data is regularly assessed to ensure that the correct decisions are being made, and any changes in user behaviour or demand can quickly be factored into the network’s energy management.
The result
Even taking into account the conservative approach taken in the beginning, the results of the trial have been hugely positive - every year, Radio Access Network (RAN) stations and electricity account for 71 percent of FET’s electricity bills, and a saving of 25 percent will make a big difference to their bottom line.
The trial also indicated that a more aggressive approach to energy management in the network could yield even greater savings and maintaining network quality, as well as identifying areas where energy is being leaked or wasted and eliminating problems before they occur.
To learn more about how and why FET decided to deploy Ericsson’s Service Continuity AI app suite and the benefits it brought, download the paper here.
