2008
DOI: 10.1109/tse.2008.30
|View full text |Cite
|
Sign up to set email alerts
|

Performance Model Estimation and Tracking Using Optimal Filters

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
92
0

Year Published

2009
2009
2021
2021

Publication Types

Select...
5
2
2

Relationship

0
9

Authors

Journals

citations
Cited by 108 publications
(92 citation statements)
references
References 22 publications
0
92
0
Order By: Relevance
“…The problem is formulated as a multivariate linear regression problem and accounts for multiple effects such as data aging. Also, several works have shown how combining the queueing theoretic formulas used by regression methods with the Kalman filter can enable continuous demand tracking [41,42].…”
Section: Workload Inferencementioning
confidence: 99%
“…The problem is formulated as a multivariate linear regression problem and accounts for multiple effects such as data aging. Also, several works have shown how combining the queueing theoretic formulas used by regression methods with the Kalman filter can enable continuous demand tracking [41,42].…”
Section: Workload Inferencementioning
confidence: 99%
“…To address this problem, our approach is to take coarse-grained measurements and apply statistical inference to estimate mean resource demands. Most of existing mean demand estimation approaches rely on the regression against utilization data [3][4][5][6][7][8][9][10][11][12][13], however, utilization measurements are not always available, for instance in Platform-as-a-Service (PaaS) deployments where the resource layer is hidden to the application and thus protected from external monitoring.…”
Section: Fg Analyzermentioning
confidence: 99%
“…Approaches to resource demand estimation can be found in [18], [19], [27]. While in [18] applies the Service Demand Law directly for single workload classes, linear regression approaches to partition resource demand among multiple workload classes can be found in [19], [28].…”
Section: Related Workmentioning
confidence: 99%
“…While in [18] applies the Service Demand Law directly for single workload classes, linear regression approaches to partition resource demand among multiple workload classes can be found in [19], [28]. In [27], utilization and throughput data is used to build a Kalman filter estimator.…”
Section: Related Workmentioning
confidence: 99%