Dynamic active window management: A method for improving revenue generation in dynamic enterprise systems

M. Al-Ghamdi; A. P. Chester; L. He; S. A. Jarvis; J. W.J. Xue

doi:10.1109/CIT.2011.91

Dynamic active window management: A method for improving revenue generation in dynamic enterprise systems

M. Al-Ghamdi^*, A. P. Chester, L. He, S. A. Jarvis, J. W.J. Xue

^*Corresponding author for this work

Engineering and Physical Sciences

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

Abstract

In dynamic resource allocation systems, servers are moved between pools when overloading is detected. In this work, we investigate the impact to such systems of combining three adaptive monitoring techniques. First we employ two well known switching policies the Proportional Switching Policy (PSP) and the Bottleneck Aware Switching Policy (BSP) to move servers between server pools as appropriate. Second we use a metaforecasting technique to predict the movement in future system workload. Third, we use a Dynamic Active Window Model (DAWM), which defines the period over which workload data is analysed. We have previously shown that request servicing capability can be improved by as much as 40% when the right combination of dynamic server switching and workload forecasting are used. This extended model shows that a further 51.5% improvement can be achieved when the switching server policy, meta-forecasting and dynamic active window management are employed together over a real-world workload based on Internet traces.

Original language	English
Title of host publication	Proceedings - 11th IEEE International Conference on Computer and Information Technology, CIT 2011
Pages	23-28
Number of pages	6
DOIs	https://doi.org/10.1109/CIT.2011.91
Publication status	Published - 2011
Event	11th IEEE International Conference on Computer and Information Technology, CIT 2011 and 11th IEEE International Conference on Scalable Computing and Communications, SCALCOM 2011 - Pafos, Cyprus Duration: 31 Aug 2011 → 2 Sept 2011

Publication series

Name	Proceedings - 11th IEEE International Conference on Computer and Information Technology, CIT 2011

Conference

Conference	11th IEEE International Conference on Computer and Information Technology, CIT 2011 and 11th IEEE International Conference on Scalable Computing and Communications, SCALCOM 2011
Country/Territory	Cyprus
City	Pafos
Period	31/08/11 → 2/09/11

Keywords

Dynamic resource allocation
Enterprise applications
Predictors
Switching policies

ASJC Scopus subject areas

Computer Networks and Communications
Information Systems

Access to Document

10.1109/CIT.2011.91

Cite this

Al-Ghamdi, M., Chester, A. P., He, L., Jarvis, S. A., & Xue, J. W. J. (2011). Dynamic active window management: A method for improving revenue generation in dynamic enterprise systems. In Proceedings - 11th IEEE International Conference on Computer and Information Technology, CIT 2011 (pp. 23-28). Article 6036586 (Proceedings - 11th IEEE International Conference on Computer and Information Technology, CIT 2011). https://doi.org/10.1109/CIT.2011.91

Al-Ghamdi, M. ; Chester, A. P. ; He, L. et al. / Dynamic active window management : A method for improving revenue generation in dynamic enterprise systems. Proceedings - 11th IEEE International Conference on Computer and Information Technology, CIT 2011. 2011. pp. 23-28 (Proceedings - 11th IEEE International Conference on Computer and Information Technology, CIT 2011).

@inproceedings{e2db4b65df4340af9c905927047bcb19,

title = "Dynamic active window management: A method for improving revenue generation in dynamic enterprise systems",

abstract = "In dynamic resource allocation systems, servers are moved between pools when overloading is detected. In this work, we investigate the impact to such systems of combining three adaptive monitoring techniques. First we employ two well known switching policies the Proportional Switching Policy (PSP) and the Bottleneck Aware Switching Policy (BSP) to move servers between server pools as appropriate. Second we use a metaforecasting technique to predict the movement in future system workload. Third, we use a Dynamic Active Window Model (DAWM), which defines the period over which workload data is analysed. We have previously shown that request servicing capability can be improved by as much as 40% when the right combination of dynamic server switching and workload forecasting are used. This extended model shows that a further 51.5% improvement can be achieved when the switching server policy, meta-forecasting and dynamic active window management are employed together over a real-world workload based on Internet traces.",

keywords = "Dynamic resource allocation, Enterprise applications, Predictors, Switching policies",

author = "M. Al-Ghamdi and Chester, {A. P.} and L. He and Jarvis, {S. A.} and Xue, {J. W.J.}",

year = "2011",

doi = "10.1109/CIT.2011.91",

language = "English",

isbn = "9780769543888",

series = "Proceedings - 11th IEEE International Conference on Computer and Information Technology, CIT 2011",

pages = "23--28",

booktitle = "Proceedings - 11th IEEE International Conference on Computer and Information Technology, CIT 2011",

note = "11th IEEE International Conference on Computer and Information Technology, CIT 2011 and 11th IEEE International Conference on Scalable Computing and Communications, SCALCOM 2011 ; Conference date: 31-08-2011 Through 02-09-2011",

}

Al-Ghamdi, M, Chester, AP, He, L, Jarvis, SA & Xue, JWJ 2011, Dynamic active window management: A method for improving revenue generation in dynamic enterprise systems. in Proceedings - 11th IEEE International Conference on Computer and Information Technology, CIT 2011., 6036586, Proceedings - 11th IEEE International Conference on Computer and Information Technology, CIT 2011, pp. 23-28, 11th IEEE International Conference on Computer and Information Technology, CIT 2011 and 11th IEEE International Conference on Scalable Computing and Communications, SCALCOM 2011, Pafos, Cyprus, 31/08/11. https://doi.org/10.1109/CIT.2011.91

Dynamic active window management: A method for improving revenue generation in dynamic enterprise systems. / Al-Ghamdi, M.; Chester, A. P.; He, L. et al.
Proceedings - 11th IEEE International Conference on Computer and Information Technology, CIT 2011. 2011. p. 23-28 6036586 (Proceedings - 11th IEEE International Conference on Computer and Information Technology, CIT 2011).

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

TY - GEN

T1 - Dynamic active window management

T2 - 11th IEEE International Conference on Computer and Information Technology, CIT 2011 and 11th IEEE International Conference on Scalable Computing and Communications, SCALCOM 2011

AU - Al-Ghamdi, M.

AU - Chester, A. P.

AU - He, L.

AU - Jarvis, S. A.

AU - Xue, J. W.J.

PY - 2011

Y1 - 2011

N2 - In dynamic resource allocation systems, servers are moved between pools when overloading is detected. In this work, we investigate the impact to such systems of combining three adaptive monitoring techniques. First we employ two well known switching policies the Proportional Switching Policy (PSP) and the Bottleneck Aware Switching Policy (BSP) to move servers between server pools as appropriate. Second we use a metaforecasting technique to predict the movement in future system workload. Third, we use a Dynamic Active Window Model (DAWM), which defines the period over which workload data is analysed. We have previously shown that request servicing capability can be improved by as much as 40% when the right combination of dynamic server switching and workload forecasting are used. This extended model shows that a further 51.5% improvement can be achieved when the switching server policy, meta-forecasting and dynamic active window management are employed together over a real-world workload based on Internet traces.

AB - In dynamic resource allocation systems, servers are moved between pools when overloading is detected. In this work, we investigate the impact to such systems of combining three adaptive monitoring techniques. First we employ two well known switching policies the Proportional Switching Policy (PSP) and the Bottleneck Aware Switching Policy (BSP) to move servers between server pools as appropriate. Second we use a metaforecasting technique to predict the movement in future system workload. Third, we use a Dynamic Active Window Model (DAWM), which defines the period over which workload data is analysed. We have previously shown that request servicing capability can be improved by as much as 40% when the right combination of dynamic server switching and workload forecasting are used. This extended model shows that a further 51.5% improvement can be achieved when the switching server policy, meta-forecasting and dynamic active window management are employed together over a real-world workload based on Internet traces.

KW - Dynamic resource allocation

KW - Enterprise applications

KW - Predictors

KW - Switching policies

UR - http://www.scopus.com/inward/record.url?scp=80055005433&partnerID=8YFLogxK

U2 - 10.1109/CIT.2011.91

DO - 10.1109/CIT.2011.91

M3 - Conference contribution

AN - SCOPUS:80055005433

SN - 9780769543888

T3 - Proceedings - 11th IEEE International Conference on Computer and Information Technology, CIT 2011

SP - 23

EP - 28

BT - Proceedings - 11th IEEE International Conference on Computer and Information Technology, CIT 2011

Y2 - 31 August 2011 through 2 September 2011

ER -

Al-Ghamdi M, Chester AP, He L, Jarvis SA, Xue JWJ. Dynamic active window management: A method for improving revenue generation in dynamic enterprise systems. In Proceedings - 11th IEEE International Conference on Computer and Information Technology, CIT 2011. 2011. p. 23-28. 6036586. (Proceedings - 11th IEEE International Conference on Computer and Information Technology, CIT 2011). doi: 10.1109/CIT.2011.91

Dynamic active window management: A method for improving revenue generation in dynamic enterprise systems

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this