On Learning Parametric Dependencies from Monitoring Data
J. Grohmann, S. Eismann, and S. Kounev. Proceedings of the 10th Symposium on Software Performance 2019 (SSP'19), (November 2019)
Abstract
A common approach to predict system performance are so-called architectural performance models. In these models, parametric dependencies describe the relation between the input parameters of a component and its performance properties and therefore significantly increase the model expressiveness. However, manually modeling parametric dependencies is often infeasible in practice. Existing automated extraction approaches require either application source code or dedicated performance tests, which are not always available. We therefore introduced one approach for identification and one for characterization of parametric dependencies, solely based on run-time monitoring data. In this paper, we propose our idea on combining both techniques in order to create a holistic approach for the identification and characterization of parametric dependencies. Furthermore, we discuss challenges we are currently facing and potential ideas on how to overcome them.
%0 Conference Paper
%1 GrEiKo2019-SSP-LearningDependencies
%A Grohmann, Johannes
%A Eismann, Simon
%A Kounev, Samuel
%B Proceedings of the 10th Symposium on Software Performance 2019 (SSP'19)
%D 2019
%K Automated_model_learning Performance Prediction Self-adaptive-systems Self-aware-computing Statistical_estimation_and_machine_learning descartes t_workshop myown
%T On Learning Parametric Dependencies from Monitoring Data
%U https://pi.informatik.uni-siegen.de/stt/39_4/01_Fachgruppenberichte/SSP2019/SSP2019_Grohmann.pdf
%X A common approach to predict system performance are so-called architectural performance models. In these models, parametric dependencies describe the relation between the input parameters of a component and its performance properties and therefore significantly increase the model expressiveness. However, manually modeling parametric dependencies is often infeasible in practice. Existing automated extraction approaches require either application source code or dedicated performance tests, which are not always available. We therefore introduced one approach for identification and one for characterization of parametric dependencies, solely based on run-time monitoring data. In this paper, we propose our idea on combining both techniques in order to create a holistic approach for the identification and characterization of parametric dependencies. Furthermore, we discuss challenges we are currently facing and potential ideas on how to overcome them.
@inproceedings{GrEiKo2019-SSP-LearningDependencies,
abstract = {A common approach to predict system performance are so-called architectural performance models. In these models, parametric dependencies describe the relation between the input parameters of a component and its performance properties and therefore significantly increase the model expressiveness. However, manually modeling parametric dependencies is often infeasible in practice. Existing automated extraction approaches require either application source code or dedicated performance tests, which are not always available. We therefore introduced one approach for identification and one for characterization of parametric dependencies, solely based on run-time monitoring data. In this paper, we propose our idea on combining both techniques in order to create a holistic approach for the identification and characterization of parametric dependencies. Furthermore, we discuss challenges we are currently facing and potential ideas on how to overcome them. },
added-at = {2020-04-06T11:25:41.000+0200},
author = {Grohmann, Johannes and Eismann, Simon and Kounev, Samuel},
biburl = {https://www.bibsonomy.org/bibtex/2ad0035c27bd5c98d2628469b1c455f5e/samuel.kounev},
booktitle = {Proceedings of the 10th Symposium on Software Performance 2019 (SSP'19)},
interhash = {8d9c421611e65c120e344d88d42ea4c5},
intrahash = {ad0035c27bd5c98d2628469b1c455f5e},
keywords = {Automated_model_learning Performance Prediction Self-adaptive-systems Self-aware-computing Statistical_estimation_and_machine_learning descartes t_workshop myown},
month = {November},
timestamp = {2021-01-13T13:24:36.000+0100},
title = {{On Learning Parametric Dependencies from Monitoring Data}},
url = {https://pi.informatik.uni-siegen.de/stt/39_4/01_Fachgruppenberichte/SSP2019/SSP2019_Grohmann.pdf},
year = 2019
}