RAI-6Green
Robust and AI Native 6G for Green Networks
Background
There is a trade-off between robustness and energy consumption of a network since extra resources are needed to guarantee robustness of the network against changing channel conditions, link failures and disasters. This trade-off is due to the rigid nature of the legacy cellular network architecture, not allowing much elasticity where network coverage is fixed, once deployed. Currently, the roll-out of 5G is ramping up in many countries and although 5G technology is much more energy-efficient than legacy networks, it consumes more energy at the current state due to its much larger capacity.
Recent advances in virtualisation, softwarization and cloudification of network resources enable us to design cloud-based, cell-less networks where processing and network resources can be dynamically reconfigured following the changing environment and end-user requirements. Networks should not consume energy when there is no user to serve, or energy consumption should scale with the services that is expected from the network.
Purpose and goal
The main goal of the RAI-6Green project is to achieve an improvement of about 30-40% of the end-to-end energy efficiency compared to current mobile networks while guaranteeing the reliability and resilience needed by that mission. This target is very challenging but possible considering results obtained by IT industries for operating data centers and access networks. These network segments are the most energy-consuming parts of the IT infrastructure.
Expected outcome
RAI-6Green is positioned on the road towards 6G networks taking advantage of different enablers that are being designed for future networks. Cloud and AI Native Open RAN, for example, will enable elasticity to dynamically reconfigure networks to meet with specific goals and to quickly react against failures. The project team expects that usage of terahertz bands needs to be considered. Hence, the key issues to be addressed by RAI-6Green are:
-
Proposal of AI-based Network Energy Efficiency and Spectral Efficiency assessment and optimization including the access, the point-of-presence and the core networks.
-
Explore solutions for accelerating computation facilities that empower AI in a distributed or centralized architecture. This item is closely related to green computing facilities.
-
Solutions for control procedures that optimize networks sites power consumption and power usage (including local solar energy) depending on a variety of parameters that could be non-correlated.
-
Proposal of risk-sensitive (delay, robustness, energy consumption, quality of service) optimization for performance management that considers the end-to-end path.
-
Proposal of smart, autonomous and parameter-free base-stations that learn from the environment and activate the relevant energy saving features when needed with the optimized parameter settings.
-
Definition of AI-based network multi-objective optimization using data (traffic prediction, resource pre-allocation, self-healing).
-
Definition of Key Performance Indicators (KPIs) for robustness and energy efficiency of network slices and adequate measurement and reporting methods (for energy efficiency standards evolutions).
-
Interconnection of 6G networks, their edge data centers and the smart grid for an opportunistic exploitation of the surplus of energy production within the edge data centers, for AI as a Service data processing.
-
Technical-economic study for AI-based, green deployment of edge computing, and proposal for co-investment plan involving stakeholders, such as network operator and service providers.
Planned approach and implementation
This project is a Celtic-Next project with 18 partners from 5 countries (Sweden, Türkiye, France, Hungary, Portugal) in total. The Swedish consortium is funded by Vinnova. The project at KTH is led by Cicek Cavdar. Four PhD students and one postdoc will work on this project.
Duration
2024-2026
Contact person
External link
See more information on: