Neural networks for web server workload forecasting

Author

Tran, Van Giang ; Debusschere, Vincent ; Bacha, Seddik

Author_Institution

Univ. Grenoble Alpes, G2Elab, Grenoble, France

fYear

2013

fDate

25-28 Feb. 2013

Firstpage

1152

Lastpage

1156

Abstract

This paper presents a comparative study of five intelligent forecast models for workload of server defined as HTTP requests. These five forecast models are based on the methodology: Nonlinear AutoRegressive model with eXogenous Inputs (NARX), Multilayer Perceptron (MLP), Elman, Cascade-Neural Network (CCNN) and Pattern Recognition Neural Network (PRNN). The best accuracy prediction is given by the NARX model. This work takes parts in development of our forecast models in the project EnergeTic-FUI, France.

Keywords

autoregressive processes; file servers; multilayer perceptrons; pattern recognition; CCNN; Elman neural network; EnergeTic-FUI; France; HTTP requests; MLP; NARX; PRNN; Web server workload forecasting; cascade-neural network; intelligent forecast models; multilayer perceptron; nonlinear autoregressive model with exogenous inputs; pattern recognition neural network; Computational modeling; Forecasting; Hidden Markov models; Neural networks; Neurons; Predictive models; Servers; EnergeTIC-FUI; Neural network; data center workload forecasting; intelligent computational; server workload;

fLanguage

English

Publisher

ieee

Conference_Titel

Industrial Technology (ICIT), 2013 IEEE International Conference on

Conference_Location

Cape Town

Print_ISBN

978-1-4673-4567-5

Electronic_ISBN

978-1-4673-4568-2

Type

conf

DOI

10.1109/ICIT.2013.6505835

Filename

6505835