DDPC : Automated Data-Driven Power-Performance Controller Design on-the-fly for Latency-sensitive Web Services
(2023) 2023 World Wide Web Conference, WWW 2023 In ACM Web Conference 2023 - Proceedings of the World Wide Web Conference, WWW 2023 p.3067-3076- Abstract
Traditional power reduction techniques such as DVFS or RAPL are challenging to use with web services because they significantly affect the services' latency and throughput. Previous work suggested the use of controllers based on control theory or machine learning to reduce performance degradation under constrained power. However, generating these controllers is challenging as every web service applications running in a data center requires a power-performance model and a fine-tuned controller. In this paper, we present DDPC, a system for autonomic data-driven controller generation for power-latency management. DDPC automates the process of designing and deploying controllers for dynamic power allocation to manage the power-performance... (More)
Traditional power reduction techniques such as DVFS or RAPL are challenging to use with web services because they significantly affect the services' latency and throughput. Previous work suggested the use of controllers based on control theory or machine learning to reduce performance degradation under constrained power. However, generating these controllers is challenging as every web service applications running in a data center requires a power-performance model and a fine-tuned controller. In this paper, we present DDPC, a system for autonomic data-driven controller generation for power-latency management. DDPC automates the process of designing and deploying controllers for dynamic power allocation to manage the power-performance trade-offs for latency-sensitive web applications such as a social network. For each application, DDPC uses system identification techniques to learn an adaptive power-performance model that captures the application's power-latency trade-offs which is then used to generate and deploy a Proportional-Integral (PI) power controller with gain-scheduling to dynamically manage the power allocation to the server running application using RAPL. We evaluate DDPC with two realistic latency-sensitive web applications under varying load scenarios. Our results show that DDPC is capable of autonomically generating and deploying controllers within a few minutes reducing the active power allocation of a web-server by more than 50% compared to state-of-the-art techniques while maintaining the latency well below the target of the application.
(Less)
- author
- Savasci, Mehmet ; Ali-Eldin, Ahmed ; Eker, Johan LU ; Robertsson, Anders LU and Shenoy, Prashant
- organization
-
- LU Profile Area: Natural and Artificial Cognition
- LTH Profile Area: AI and Digitalization
- Department of Automatic Control
- ELLIIT: the Linköping-Lund initiative on IT and mobile communication
- LTH Profile Area: Circular Building Sector
- LTH Profile Area: Engineering Health
- eSSENCE: The e-Science Collaboration
- publishing date
- 2023-04-30
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- datacenter, power-management, Web service performance
- host publication
- ACM Web Conference 2023 - Proceedings of the World Wide Web Conference, WWW 2023
- series title
- ACM Web Conference 2023 - Proceedings of the World Wide Web Conference, WWW 2023
- pages
- 10 pages
- publisher
- Association for Computing Machinery (ACM)
- conference name
- 2023 World Wide Web Conference, WWW 2023
- conference location
- Austin, United States
- conference dates
- 2023-04-30 - 2023-05-04
- external identifiers
-
- scopus:85159298066
- ISBN
- 9781450394161
- DOI
- 10.1145/3543507.3583437
- language
- English
- LU publication?
- yes
- id
- 295d9fbb-f5eb-47f4-a1ed-f6238e414c66
- date added to LUP
- 2023-08-11 12:58:28
- date last changed
- 2023-11-22 20:56:59
@inproceedings{295d9fbb-f5eb-47f4-a1ed-f6238e414c66, abstract = {{<p>Traditional power reduction techniques such as DVFS or RAPL are challenging to use with web services because they significantly affect the services' latency and throughput. Previous work suggested the use of controllers based on control theory or machine learning to reduce performance degradation under constrained power. However, generating these controllers is challenging as every web service applications running in a data center requires a power-performance model and a fine-tuned controller. In this paper, we present DDPC, a system for autonomic data-driven controller generation for power-latency management. DDPC automates the process of designing and deploying controllers for dynamic power allocation to manage the power-performance trade-offs for latency-sensitive web applications such as a social network. For each application, DDPC uses system identification techniques to learn an adaptive power-performance model that captures the application's power-latency trade-offs which is then used to generate and deploy a Proportional-Integral (PI) power controller with gain-scheduling to dynamically manage the power allocation to the server running application using RAPL. We evaluate DDPC with two realistic latency-sensitive web applications under varying load scenarios. Our results show that DDPC is capable of autonomically generating and deploying controllers within a few minutes reducing the active power allocation of a web-server by more than 50% compared to state-of-the-art techniques while maintaining the latency well below the target of the application.</p>}}, author = {{Savasci, Mehmet and Ali-Eldin, Ahmed and Eker, Johan and Robertsson, Anders and Shenoy, Prashant}}, booktitle = {{ACM Web Conference 2023 - Proceedings of the World Wide Web Conference, WWW 2023}}, isbn = {{9781450394161}}, keywords = {{datacenter; power-management; Web service performance}}, language = {{eng}}, month = {{04}}, pages = {{3067--3076}}, publisher = {{Association for Computing Machinery (ACM)}}, series = {{ACM Web Conference 2023 - Proceedings of the World Wide Web Conference, WWW 2023}}, title = {{DDPC : Automated Data-Driven Power-Performance Controller Design on-the-fly for Latency-sensitive Web Services}}, url = {{http://dx.doi.org/10.1145/3543507.3583437}}, doi = {{10.1145/3543507.3583437}}, year = {{2023}}, }