Dear visitor, please be informed that this is the ITEA staging environment. No actions here will be updated to production, feel free to test the system
Reinforcement learning for energy improvements in data centers
- Project
- 17002 AutoDC
- Type
- New standard
- Description
- Online algorithm for workload and facility management to reduce energy usage through reinforcement learning.
- Demonstrates around 60% improved power usage efficiency (PUE) over the already world-class RISE ICE data center.
- The proposed holistic approach to datacenter management is cuttingedge.
- Publication: A. Heimerson, R. Brännvall, J. Sjölund, J. Eker, J. Gustafsson, ”Towards a Holistic Controller: Reinforcement Learning for Data Center Control”, 9th International Workshop on Energy-Efficient Data Centres (E2 DC 2021).
- Contact
- Karl-Erik Årzén
- karl-erik.arzen@control.lth.se
- Technical features
Input(s):
- Connected datacenter.
Main feature(s):
- Energy efficient control of cloud services using reinforcement learning.
Output(s):
- Algorithms
- Integration constraints
None
- Targeted customer(s)
- Developers
- Researchers
- Conditions for reuse
Algorithms
- Confidentiality
- Public
- Publication date
- 01-09-2021
- Involved partners
- Lund University (SWE)