TY - JOUR
T1 - An α-stable model-based linear-parameter-varying control for managing server performance under self-similar workloads
AU - Qin, Wubi
AU - Wang, Qian
AU - Sivasubramiam, Anand
N1 - Funding Information:
Manuscript received July 03, 2007; revised January 02, 2008. Manuscript received in final form April 10, 2008. First published June 26, 2008; current version published December 24, 2008. Recommended by Associate Editor S. Borst. This work was supported in part by the National Science Foundation under Grant 0323056.
PY - 2009
Y1 - 2009
N2 - Applying control-theoretic approaches to capacity provisioning and performance management of web servers is gaining increasing popularity in the past several years. This paper presents a novel control-theoretic approach that is a combination of linear-parameter-varying (LPV) techniques and workload characterization using α-stable-model based stochastic envelopes. In particular, we parameterize a control-oriented web-server model and resulting controller using scheduling variables that are workload-distribution parameters. By further applying an α-stable modeling technique to identify the load parameters and using them to online schedule the LPV model and controller, the presented solutions not only allow the system to adapt to load variations, but also show great promise in handling self-similar workloads. The proposed framework is applied to a web-server CPU management problem, where the server CPU frequencies are dynamically tuned and implemented via the dynamic voltage scaling mechanism to achieve the target response time. Simulations using real web-server traces are conducted to show the strength of the proposed approach.
AB - Applying control-theoretic approaches to capacity provisioning and performance management of web servers is gaining increasing popularity in the past several years. This paper presents a novel control-theoretic approach that is a combination of linear-parameter-varying (LPV) techniques and workload characterization using α-stable-model based stochastic envelopes. In particular, we parameterize a control-oriented web-server model and resulting controller using scheduling variables that are workload-distribution parameters. By further applying an α-stable modeling technique to identify the load parameters and using them to online schedule the LPV model and controller, the presented solutions not only allow the system to adapt to load variations, but also show great promise in handling self-similar workloads. The proposed framework is applied to a web-server CPU management problem, where the server CPU frequencies are dynamically tuned and implemented via the dynamic voltage scaling mechanism to achieve the target response time. Simulations using real web-server traces are conducted to show the strength of the proposed approach.
UR - http://www.scopus.com/inward/record.url?scp=58249127923&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=58249127923&partnerID=8YFLogxK
U2 - 10.1109/TCST.2008.924555
DO - 10.1109/TCST.2008.924555
M3 - Article
AN - SCOPUS:58249127923
SN - 1063-6536
VL - 17
SP - 123
EP - 134
JO - IEEE Transactions on Control Systems Technology
JF - IEEE Transactions on Control Systems Technology
IS - 1
ER -