Descripción
|
|
---|---|
Cloud infrastructure in data centers is expected to be one of the main technologies supporting Internet communications in the coming years. Virtualization is employed to achieve the flexibility and dynamicity required by the wide variety of applications used today. Therefore, optimal allocation of virtual machines is key to ensuring performance and efficiency. Noisy neighbor is a term used to describe virtual machines competing for physical resources and thus disturbing each other, a phenomenon that can dramatically degrade their performance. Detecting noisy neighbors using simple thresholding approaches is ineffective. To exploit the time-series nature of cloud monitoring data, we propose an approach based on deep convolutional networks. We test it on real infrastructure data and show it outperforms well-known classifiers in detecting noisy neighbors. | |
Internacional
|
Si |
Nombre congreso
|
European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. |
Tipo de participación
|
960 |
Lugar del congreso
|
Brujas, Belgica |
Revisores
|
Si |
ISBN o ISSN
|
978-28-7587-039-1 |
DOI
|
|
Fecha inicio congreso
|
26/04/2017 |
Fecha fin congreso
|
28/04/2017 |
Desde la página
|
571 |
Hasta la página
|
576 |
Título de las actas
|
ESANN 2017 proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. |