In this paper, we present the Framework for building Failure Prediction Models ((FPM)-P-2), a Machine Learning-based Framework to build models for predicting the Remaining Time to Failure (RTTF) of applications in the presence of software anomalies. (FPM)-P-2 uses measurements of a number of system features in order to create a knowledge base, which is then used to build prediction models. (FPM)-P-2 is application-independent, i.e. it solely exploits measurements of system-level features. Thus, it can be used in differentiated contexts, without the need for any manual modification or intervention to the running applications. To generate optimized models, (FPM)-P-2 can perform a feature selection to identify, among all the measured system features, which have a major impact in the prediction of the RTTF. This allows to produce different models, which use different set of input features. Generated models can be compared by the user by using a set of metrics produced by (FPM)-P-2, which are related to the model prediction accuracy, as well as to the model building time. We also present experimental results of a successful application of (FPM)-P-2, using the standard TPC-W e-commerce benchmark.
Pellegrini, A., Di Sanzo, P., Avresky, D.r. (2015). A Machine Learning-based Framework for Building Application Failure Prediction Models. In 2015 IEEE International Parallel and Distributed Processing Symposium Workshop (pp.1072-1081). 345 E 47TH ST, NEW YORK, NY 10017 USA : IEEE [10.1109/IPDPSW.2015.110].
A Machine Learning-based Framework for Building Application Failure Prediction Models
Alessandro Pellegrini
;
2015-05-01
Abstract
In this paper, we present the Framework for building Failure Prediction Models ((FPM)-P-2), a Machine Learning-based Framework to build models for predicting the Remaining Time to Failure (RTTF) of applications in the presence of software anomalies. (FPM)-P-2 uses measurements of a number of system features in order to create a knowledge base, which is then used to build prediction models. (FPM)-P-2 is application-independent, i.e. it solely exploits measurements of system-level features. Thus, it can be used in differentiated contexts, without the need for any manual modification or intervention to the running applications. To generate optimized models, (FPM)-P-2 can perform a feature selection to identify, among all the measured system features, which have a major impact in the prediction of the RTTF. This allows to produce different models, which use different set of input features. Generated models can be compared by the user by using a set of metrics produced by (FPM)-P-2, which are related to the model prediction accuracy, as well as to the model building time. We also present experimental results of a successful application of (FPM)-P-2, using the standard TPC-W e-commerce benchmark.File | Dimensione | Formato | |
---|---|---|---|
Pell15.pdf
solo utenti autorizzati
Tipologia:
Documento in Pre-print
Licenza:
Copyright dell'editore
Dimensione
375.87 kB
Formato
Adobe PDF
|
375.87 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.