Your browser doesn't support javascript. This means that the content or functionality of our website will be limited or unavailable. If you need more information about Vinnova, please contact us.

EUREKA Celtic-Plus Artificial Intelligence for Green Networks (AI4Green)

Reference number
Coordinator Kungliga Tekniska Högskolan - Communication Systems
Funding from Vinnova SEK 10 548 134
Project duration January 2019 - December 2022
Status Completed
Venture Eureka cluster co-funding 

Purpose and goal

The overall goal for the AI4Green project has been to save energy in mobile communication networks of 30-40% by utilization of AI assisted control and fault detection. The goal of saving energy has been fulfilled by development of a number of technologies and solutions such as AI based control of network elements, fault detection, simulations, experiments and radar supported ray tracing.

Expected results and effects

A direct result of results is that the participating operators Tele2 and Turkcell can now, with the help of the project results, save energy in different ways in their existing (4G/LTE) and future (5G+) radio networks. In principle, the results are not tied only to these actors, they have partly been spread in public form and can therefore be used on a general basis.

Planned approach and implementation

Since its inception, AI4Green has consisted of partners from 5 countries (Sweden, Finland, Turkey, France and Portugal). Great emphasis was placed on including research organization stations, small innovative suppliers and operators (also consumers of energy). The complexity in the number of countries and partners caused a delay in starting the activities, but the project has delivered according to its own set objective. Activities have included simulations and calculations, measurements, demonstrations, live tests and publications.

External links

The project description has been provided by the project members themselves and the text has not been looked at by our editors.

Last updated 16 May 2023

Reference number 2018-03032

Page statistics