Robust control-theoretic thermal balancing for server clusters

Yong Fu; Chenyang Lu; Hongan Wang

doi:10.1109/IPDPS.2010.5470480

Robust control-theoretic thermal balancing for server clusters

Yong Fu
, Chenyang Lu
, Hongan Wang

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

13 Scopus citations

Abstract

Thermal management is critical for clusters because of the increasing power consumption of modern processors, compact server architectures and growing server density in data centers. Thermal balancing mitigates hot spots in a cluster through dynamic load distribution among servers. This paper presents two Control-theoretical Thermal Balancing (CTB) algorithms that dynamically balance the temperatures of different servers based on online measurements. CTB features controllers rigorously designed based on optimal control theory and a difference equation model that approximates the thermal dynamics of clusters. Control analysis and simulation results demonstrate that CTB achieves robust thermal balancing under a wide range of uncertainties: (1) when different tasks incur different power consumptions on the CPUs, (2) when servers experience different ambient temperatures, and (3) when servers experience thermal faults.

Original language	English
Title of host publication	Proceedings of the 2010 IEEE International Symposium on Parallel and Distributed Processing, IPDPS 2010
DOIs	https://doi.org/10.1109/IPDPS.2010.5470480
State	Published - 2010
Event	24th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2010 - Atlanta, GA, United States Duration: Apr 19 2010 → Apr 23 2010

Publication series

Name	Proceedings of the 2010 IEEE International Symposium on Parallel and Distributed Processing, IPDPS 2010

Conference

Conference	24th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2010
Country/Territory	United States
City	Atlanta, GA
Period	04/19/10 → 04/23/10

Keywords

Clusters
Feedback control
Thermal balancing

Access to Document

10.1109/IPDPS.2010.5470480

Cite this

Fu, Y., Lu, C., & Wang, H. (2010). Robust control-theoretic thermal balancing for server clusters. In Proceedings of the 2010 IEEE International Symposium on Parallel and Distributed Processing, IPDPS 2010 Article 5470480 (Proceedings of the 2010 IEEE International Symposium on Parallel and Distributed Processing, IPDPS 2010). https://doi.org/10.1109/IPDPS.2010.5470480

@inproceedings{b8e5d73ba8684de0adfdb021cd35179d,

title = "Robust control-theoretic thermal balancing for server clusters",

abstract = "Thermal management is critical for clusters because of the increasing power consumption of modern processors, compact server architectures and growing server density in data centers. Thermal balancing mitigates hot spots in a cluster through dynamic load distribution among servers. This paper presents two Control-theoretical Thermal Balancing (CTB) algorithms that dynamically balance the temperatures of different servers based on online measurements. CTB features controllers rigorously designed based on optimal control theory and a difference equation model that approximates the thermal dynamics of clusters. Control analysis and simulation results demonstrate that CTB achieves robust thermal balancing under a wide range of uncertainties: (1) when different tasks incur different power consumptions on the CPUs, (2) when servers experience different ambient temperatures, and (3) when servers experience thermal faults.",

keywords = "Clusters, Feedback control, Thermal balancing",

author = "Yong Fu and Chenyang Lu and Hongan Wang",

year = "2010",

doi = "10.1109/IPDPS.2010.5470480",

language = "English",

isbn = "9781424464432",

series = "Proceedings of the 2010 IEEE International Symposium on Parallel and Distributed Processing, IPDPS 2010",

booktitle = "Proceedings of the 2010 IEEE International Symposium on Parallel and Distributed Processing, IPDPS 2010",

note = "24th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2010 ; Conference date: 19-04-2010 Through 23-04-2010",

}

Fu, Y, Lu, C & Wang, H 2010, Robust control-theoretic thermal balancing for server clusters. in Proceedings of the 2010 IEEE International Symposium on Parallel and Distributed Processing, IPDPS 2010., 5470480, Proceedings of the 2010 IEEE International Symposium on Parallel and Distributed Processing, IPDPS 2010, 24th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2010, Atlanta, GA, United States, 04/19/10. https://doi.org/10.1109/IPDPS.2010.5470480

Robust control-theoretic thermal balancing for server clusters. / Fu, Yong; Lu, Chenyang; Wang, Hongan.
Proceedings of the 2010 IEEE International Symposium on Parallel and Distributed Processing, IPDPS 2010. 2010. 5470480 (Proceedings of the 2010 IEEE International Symposium on Parallel and Distributed Processing, IPDPS 2010).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Robust control-theoretic thermal balancing for server clusters

AU - Fu, Yong

AU - Lu, Chenyang

AU - Wang, Hongan

PY - 2010

Y1 - 2010

N2 - Thermal management is critical for clusters because of the increasing power consumption of modern processors, compact server architectures and growing server density in data centers. Thermal balancing mitigates hot spots in a cluster through dynamic load distribution among servers. This paper presents two Control-theoretical Thermal Balancing (CTB) algorithms that dynamically balance the temperatures of different servers based on online measurements. CTB features controllers rigorously designed based on optimal control theory and a difference equation model that approximates the thermal dynamics of clusters. Control analysis and simulation results demonstrate that CTB achieves robust thermal balancing under a wide range of uncertainties: (1) when different tasks incur different power consumptions on the CPUs, (2) when servers experience different ambient temperatures, and (3) when servers experience thermal faults.

AB - Thermal management is critical for clusters because of the increasing power consumption of modern processors, compact server architectures and growing server density in data centers. Thermal balancing mitigates hot spots in a cluster through dynamic load distribution among servers. This paper presents two Control-theoretical Thermal Balancing (CTB) algorithms that dynamically balance the temperatures of different servers based on online measurements. CTB features controllers rigorously designed based on optimal control theory and a difference equation model that approximates the thermal dynamics of clusters. Control analysis and simulation results demonstrate that CTB achieves robust thermal balancing under a wide range of uncertainties: (1) when different tasks incur different power consumptions on the CPUs, (2) when servers experience different ambient temperatures, and (3) when servers experience thermal faults.

KW - Clusters

KW - Feedback control

KW - Thermal balancing

UR - https://www.scopus.com/pages/publications/77953998244

U2 - 10.1109/IPDPS.2010.5470480

DO - 10.1109/IPDPS.2010.5470480

M3 - Conference contribution

AN - SCOPUS:77953998244

SN - 9781424464432

T3 - Proceedings of the 2010 IEEE International Symposium on Parallel and Distributed Processing, IPDPS 2010

BT - Proceedings of the 2010 IEEE International Symposium on Parallel and Distributed Processing, IPDPS 2010

T2 - 24th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2010

Y2 - 19 April 2010 through 23 April 2010

ER -

Robust control-theoretic thermal balancing for server clusters

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this