info:eu-repo/semantics/article
Learning Running-time Prediction Models for Gene-Expression Analysis Workflows
Fecha
2015-09Registro en:
Monge Bosdari, David Antonio; Holec, Matej; Zelezny, Filip; Garcia Garino, Carlos Gabriel; Learning Running-time Prediction Models for Gene-Expression Analysis Workflows; Institute of Electrical and Electronics Engineers; IEEE Latin America Transactions; 13; 9; 9-2015; 3088-3095
1548-0992
CONICET Digital
CONICET
Autor
Monge Bosdari, David Antonio
Holec, Matej
Zelezny, Filip
Garcia Garino, Carlos Gabriel
Resumen
One of the central issues for the efficient management of Scientific workflow applications is the prediction of tasks performance. This paper proposes a novel approach for constructing performance models for tasks in data-intensivescientific workflows in an autonomous way. Ensemble Machine Learning techniques are used to produce robust combined models with high predictive accuracy. Information derived from workflow systems and the characteristics and provenance of the data are exploited to guarantee the accuracy of the models. Agene-expression analysis workflow application was used as case study over homogeneous and heterogeneous computing environments. Experimental results evidence noticeable improvements while using ensemble models in comparison withsingle/standalone prediction models. Ensemble learning techniques made it possible to reduce the prediction error with respect to the strategies of a single-model with values ranging from 14.47% to 28.36% for the homogeneous case, and from 8.34% to 17.18% for the heterogeneous case.