In this paper, we present the Framework for building Failure Prediction Models (F2PM), a Machine Learning-based Framework to build models for predicting the Remaining Time to Failure (RTTF) of applications in the presence of software anomalies. F2PM uses measurements of a number of system features in order to create a knowledge base, which is then used to build prediction models. F2PM 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, F2PM 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 F2PM, 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 F2PM, using the standard TPC-W e-commerce benchmark.

A Machine Learning-based Framework for Building Application Failure Prediction Models

DI SANZO, PIERANGELO;
2015

Abstract

In this paper, we present the Framework for building Failure Prediction Models (F2PM), a Machine Learning-based Framework to build models for predicting the Remaining Time to Failure (RTTF) of applications in the presence of software anomalies. F2PM uses measurements of a number of system features in order to create a knowledge base, which is then used to build prediction models. F2PM 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, F2PM 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 F2PM, 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 F2PM, using the standard TPC-W e-commerce benchmark.
0-7695-5510-1
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11697/160349
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 17
  • ???jsp.display-item.citation.isi??? 11
social impact