Enhancing regression models for complex systems using evolutionary techniques for feature engineering

Arroba García, Patricia; Risco Martín, José Luis; Zapater Sancho, Marina; Moya Fernández, José Manuel y Ayala Rodrigo, José Luis (2014). Enhancing regression models for complex systems using evolutionary techniques for feature engineering. "Journal of Grid Computing" ; pp. 1-15. ISSN 1570-7873. https://doi.org/10.1007/s10723-014-9313-8.

Descripción

Título: Enhancing regression models for complex systems using evolutionary techniques for feature engineering
Autor/es:
  • Arroba García, Patricia
  • Risco Martín, José Luis
  • Zapater Sancho, Marina
  • Moya Fernández, José Manuel
  • Ayala Rodrigo, José Luis
Tipo de Documento: Artículo
Título de Revista/Publicación: Journal of Grid Computing
Fecha: Septiembre 2014
Materias:
Palabras Clave Informales: Automatic modeling, Complex systems, Grammatical evolution, Classical regression, Green data centers, Sustainable cloud computing, Power modeling
Escuela: E.T.S.I. Telecomunicación (UPM)
Departamento: Ingeniería Electrónica
Licencias Creative Commons: Reconocimiento - Sin obra derivada - No comercial

Texto completo

[img]
Vista Previa
PDF (Document Portable Format) - Se necesita un visor de ficheros PDF, como GSview, Xpdf o Adobe Acrobat Reader
Descargar (2MB) | Vista Previa

Resumen

This work proposes an automatic methodology for modeling complex systems. Our methodology is based on the combination of Grammatical Evolution and classical regression to obtain an optimal set of features that take part of a linear and convex model. This technique provides both Feature Engineering and Symbolic Regression in order to infer accurate models with no effort or designer's expertise requirements. As advanced Cloud services are becoming mainstream, the contribution of data centers in the overall power consumption of modern cities is growing dramatically. These facilities consume from 10 to 100 times more power per square foot than typical office buildings. Modeling the power consumption for these infrastructures is crucial to anticipate the effects of aggressive optimization policies, but accurate and fast power modeling is a complex challenge for high-end servers not yet satisfied by analytical approaches. For this case study, our methodology minimizes error in power prediction. This work has been tested using real Cloud applications resulting on an average error in power estimation of 3.98%. Our work improves the possibilities of deriving Cloud energy efficient policies in Cloud data centers being applicable to other computing environments with similar characteristics.

Más información

ID de Registro: 35716
Identificador DC: http://oa.upm.es/35716/
Identificador OAI: oai:oa.upm.es:35716
Identificador DOI: 10.1007/s10723-014-9313-8
URL Oficial: http://link.springer.com/article/10.1007%2Fs10723-014-9313-8
Depositado por: Memoria Investigacion
Depositado el: 22 Jun 2015 17:11
Ultima Modificación: 01 Oct 2015 22:56
  • Open Access
  • Open Access
  • Sherpa-Romeo
    Compruebe si la revista anglosajona en la que ha publicado un artículo permite también su publicación en abierto.
  • Dulcinea
    Compruebe si la revista española en la que ha publicado un artículo permite también su publicación en abierto.
  • Recolecta
  • e-ciencia
  • Observatorio I+D+i UPM
  • OpenCourseWare UPM