The Luxembourg Institute of Science and Technology (LIST) and Orange Luxembourg have launched RAISE — Radio Access Intelligence for Saving Energy. Backed by the Luxembourg National Research Fund (FNR) and the Minister of the economy, the 36-month project will deploy AI across Orange Luxembourg’s nationwide network to cut electricity use, reduce carbon emissions and advance Luxembourg’s digital sustainability goals.
A network that never sleeps and consumes accordingly
Every time you make a call, stream a video or load a webpage on your phone, the signal passes through a network of antennas and transmitters spread across the country. These installations run around the clock, regardless of whether it is rush hour or the middle of the night. In fact, this part of the network, known as the Radio Access Network (RAN), accounts for more than three quarters of an operator’s entire electricity bill.
Until now, operators have had limited tools to adjust energy use in real time. RAISE aims to change that, by teaching the network to be smarter about when and how it uses energy. It also looks at future trends towards 6G, which promises way more complex RAN solutions and thus increased opportunities to optimise energy consumption
A virtual replica before any real-world risk
Before making any changes to Orange Luxembourg’s live network, the RAISE team will build a detailed virtual copy of it. This digital twin will let researchers test different energy-saving ideas safely: what happens if certain antennas are put into a low-power mode at night? Which frequency bands are the most efficient at a given time of day? The sandbox Full power will provide answers without any risk to users’ connections.
This digital twin will be fed with real data from Orange Luxembourg’s network: traffic figures updated frequently, electricity consumption readings from smart meters installed at each site, and technical performance logs. All data will be anonymized and handled in full compliance with European privacy rules.
“With RAISE, we are taking AI out of the simulation lab and putting it to work on one of the most energy-intensive parts of our daily digital lives. Using real data from a live operator is what makes the difference. It means the solutions we develop will actually work when deployed, not just in theory,” said Sébastien Faye, head of the Head of Distributed & Intelligent Connectivity Research Group at LIST.
What sets RAISE apart from generic solutions is the unique nature of Luxembourg itself. The AI models will be trained and tested on real-world conditions specific to the country: the sharp surge in mobile traffic during weekday rush hours driven by the large cross-border workforce, and the notably quieter weekends when that commuter population returns home. These patterns are unlike those of any other European country, and accounting for them is precisely what will make the solutions developed by RAISE both accurate and effective.
Artificial intelligence as a network manager
The project will develop a set of AI tools, each with a specific job. One will predict how busy the network will be in the next 24 hours, much like a weather forecast, but for mobile traffic. Another will use those predictions to decide which antennas can be safely switched to a low-power state and when. A third will manage the batteries installed at some sites, charging them when electricity is cheap and drawing on them when demand peaks.
Together, these tools are expected to reduce electricity consumption by at least 10% across Orange Luxembourg’s network without users noticing any difference in their service.
“By leveraging artificial intelligence in collaboration with the Luxembourg Institute of Science and Technology (LIST), we are optimizing our network management to reduce energy consumption by at least 10%, while ensuring an impeccable quality of service. This initiative reflects our commitment to a more responsible and sustainable digital future,” explained Christophe Van Yck, Head of Network & Strategic Projects, Orange Luxembourg.
The project runs until 2029 and is aligned with European goals to make the next generation of mobile networks significantly more energy-efficient.