Towards a Holistic Controller: Reinforcement Learning for Data Center Control
(2021) p.424-429- Abstract
- The increased use of cloud and other large scale datacenter IT services and the associated power usage has put the spotlight on more energy-efficient datacenter management. In this paper, a simple model was developed to represent the heat rejection system and energy usage in a small DC setup. The model was then controlled by a reinforcement learning agent that handles both the load balancing of the IT workload, as well as cooling system setpoints.
The main contribution is the holistic approach to datacenter control where both facility metrics, IT hardware metric and cloud service logs are used as inputs.
The application of reinforcement learning in the proposed holistic setup is feasible and achieves results that outperform... (More) - The increased use of cloud and other large scale datacenter IT services and the associated power usage has put the spotlight on more energy-efficient datacenter management. In this paper, a simple model was developed to represent the heat rejection system and energy usage in a small DC setup. The model was then controlled by a reinforcement learning agent that handles both the load balancing of the IT workload, as well as cooling system setpoints.
The main contribution is the holistic approach to datacenter control where both facility metrics, IT hardware metric and cloud service logs are used as inputs.
The application of reinforcement learning in the proposed holistic setup is feasible and achieves results that outperform standard algorithms. The paper presents both the simplified DC model and the reinforcement learning agent in detail and discusses how this work can be extended towards a richer datacenter model. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/d66f5dd6-136e-4f4c-abb6-4fde1fc14902
- author
- Heimerson, Albin LU ; Brännvall, Rickard ; Sjölund, Johannes ; Eker, Johan LU and Gustafsson, Jonas
- organization
- publishing date
- 2021-06-28
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- e-Energy '21: Proceedings of the Twelfth ACM International Conference on Future Energy Systems
- pages
- 424 - 429
- external identifiers
-
- scopus:85109345830
- DOI
- 10.1145/3447555.3466581
- project
- AutoDC
- language
- English
- LU publication?
- yes
- id
- d66f5dd6-136e-4f4c-abb6-4fde1fc14902
- date added to LUP
- 2021-07-29 11:52:12
- date last changed
- 2023-11-23 05:22:18
@inproceedings{d66f5dd6-136e-4f4c-abb6-4fde1fc14902, abstract = {{The increased use of cloud and other large scale datacenter IT services and the associated power usage has put the spotlight on more energy-efficient datacenter management. In this paper, a simple model was developed to represent the heat rejection system and energy usage in a small DC setup. The model was then controlled by a reinforcement learning agent that handles both the load balancing of the IT workload, as well as cooling system setpoints.<br/>The main contribution is the holistic approach to datacenter control where both facility metrics, IT hardware metric and cloud service logs are used as inputs. <br/>The application of reinforcement learning in the proposed holistic setup is feasible and achieves results that outperform standard algorithms. The paper presents both the simplified DC model and the reinforcement learning agent in detail and discusses how this work can be extended towards a richer datacenter model.}}, author = {{Heimerson, Albin and Brännvall, Rickard and Sjölund, Johannes and Eker, Johan and Gustafsson, Jonas}}, booktitle = {{e-Energy '21: Proceedings of the Twelfth ACM International Conference on Future Energy Systems}}, language = {{eng}}, month = {{06}}, pages = {{424--429}}, title = {{Towards a Holistic Controller: Reinforcement Learning for Data Center Control}}, url = {{https://lup.lub.lu.se/search/files/119790558/E2DC2021_RL_for_DC_control.pdf}}, doi = {{10.1145/3447555.3466581}}, year = {{2021}}, }