A Proactive Cloud Application Auto-Scaler using Reinforcement Learning
(2022) 15th ACM-IEEE International Conference on Formal Methods and Models for System Design- Abstract
- This work explores the use of reinforcement learning to design a proactive cloud resource auto-scaler that is able to predict usage across a distributed microservice application. The focus is on serving time-sensitive workloads, e.g., industrial automation, connected XR/VR (eXtended Reality/Virtual Reality), etc., where each job has a deadline and there is some cost associated with missing a deadline. A simple workload model, as well as a microservice application model, is presented. A reinforcement learning agent is trained to identify workloads and predict needed utilization for identified service chains. The results are compared to standard purely reactive techniques.
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/980385f4-ff4b-413b-af01-554c56552369
- author
- Heimerson, Albin LU ; Eker, Johan LU and Årzén, Karl-Erik LU
- organization
- publishing date
- 2022-12-06
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- epub
- subject
- host publication
- UCC '22: Proceedings of the 15th IEEE/ACM International Conference on Utility and Cloud Computing
- conference name
- 15th ACM-IEEE International Conference on Formal Methods and Models for System Design
- conference location
- New York, United States
- conference dates
- 2017-09-29 - 2017-10-02
- external identifiers
-
- scopus:85150676569
- ISBN
- 9781665460873
- DOI
- 10.1109/UCC56403.2022.00040
- project
- AutoDC
- Event-Based Control of Stochastic Systems with Application to Server Systems
- language
- English
- LU publication?
- yes
- id
- 980385f4-ff4b-413b-af01-554c56552369
- date added to LUP
- 2023-01-23 14:27:02
- date last changed
- 2023-11-22 16:43:04
@inproceedings{980385f4-ff4b-413b-af01-554c56552369, abstract = {{This work explores the use of reinforcement learning to design a proactive cloud resource auto-scaler that is able to predict usage across a distributed microservice application. The focus is on serving time-sensitive workloads, e.g., industrial automation, connected XR/VR (eXtended Reality/Virtual Reality), etc., where each job has a deadline and there is some cost associated with missing a deadline. A simple workload model, as well as a microservice application model, is presented. A reinforcement learning agent is trained to identify workloads and predict needed utilization for identified service chains. The results are compared to standard purely reactive techniques.}}, author = {{Heimerson, Albin and Eker, Johan and Årzén, Karl-Erik}}, booktitle = {{UCC '22: Proceedings of the 15th IEEE/ACM International Conference on Utility and Cloud Computing}}, isbn = {{9781665460873}}, language = {{eng}}, month = {{12}}, title = {{A Proactive Cloud Application Auto-Scaler using Reinforcement Learning}}, url = {{https://lup.lub.lu.se/search/files/141037039/DML_ICC_2022_ServiceMeshRL_short_No_template_.pdf}}, doi = {{10.1109/UCC56403.2022.00040}}, year = {{2022}}, }