Artificial Intelligence for Green networks

Project Key Information

Project Status: running

Start Date: September 2019

End Date: December 2022

Budget (total): 6092.83 K€

Effort:  66.4 PY

Project-ID: C2018/1-5

Project Coordinator

Name: Cicek Cavdar

Company: KTH Royal Institute of Technology

Country: Sweden

E-mail: cavdar(Replace this parenthesis with the @ sign)

Project Consortium

DA Group, Finland

University of Oulu, Finland

Verkotan Oy, Finland

VTT Technical Research Centre of Finland Ltd., Finland

Orange SA, France

Institute Mines Télécom, France

Allbesmart, Portugal

Celfinet, Portugal

Instituto Politecnico de Castelo Branco, Portugal

Instituto Superior de Engenharia de Lisboa, Portugal

Royal Institute of Technology, KTH, Sweden

Tele2 Sverige AB, Sweden

Canaima, Sweden

BI Nordic, Sweden

Turkcell, Turkey

P.I. Works, Turkey

Not yet active:

Turkgen, Turkey


The exponential growth of mobile traffic, associated with the emergence of new services and the expected explosion of the number of connected objects, i.e., Internet of Things (IoT) will make effective monitoring, modeling, and overall control of network traffic difficult if not impossible. Hence there is a need for powerful methods to solve the challenges faced in network design, deployment, and management. Artificial Intelligence and Machine learning have been successfully applied to various domains such as medicine, finance and astronomy, to name a few. This success suggests that these techniques could be successfully applied in the context of wireless networks to improve the overall performance and efficiency.

AI4Green is built around the need to build comprehensive, sophisticated and energy-efficient algorithms and solutions at both radio access and core networks, but also on data centers and storage while keeping in mind the emergence of new architectures and the development of smart grids. This includes:

  • Proposal of AI-based Network Energy Efficiency and Spectral Efficiency assessment and optimization
  • Proposal of AI-based demand response service for the interaction between telecom networks and smart grids
  • Explore solutions for accelerating computation facilities that empower AI in a distributed or centralized architecture
  • Solutions for control procedures that optimize networks sites power consumption and power usage depending on a variety of parameters that could be non-correlated
  • Proposal of risk-sensitive optimization for performance management that takes into account the  end-to-end  path
  • Proposal of smart, autonomous and parameter-free BSs that learn from the environment and activate the relevant energy saving features when needed with the optimized parameter settings
  • Definition of AI-based Network optimization using data (Traffic prediction, resource reallocation, self-healing)
  • Definition of KPIs for energy efficiency of network slices and adequate measurement and reporting methods (for energy efficiency standards evolutions)

The project will also consider services based on heterogeneous data collection. The main purpose is to study new business services not only for enhancing the connectivity but also to build business models based on AI such as energy as a service, connectivity market places, and smart cities. Indeed, new application domains and territories are accounting on telecom networks to facilitate their usage. The 5th generation of telecom networks is built to address those vertical ls and they will generate an amount of variable and uncorrelated data that we aim to use as inputs to orchestrate their behavior.

AI4Green is an industry-driven project where practical solutions and demonstrators are privileged, in addition to theoretical and simulation studies. The project aims to implement developed innovative solutions in terms of hardware and software trough testbeds that allow showing the effectiveness of the solutions as well as the input requirements for empowering such models.

Contact Us

We're not around right now. But you can send us an email and we'll get back to you, asap.