Self-Organizing maps for detecting abnormal thermal behavior in data centers

Aransay, Ignacio; Zapater Sancho, Marina; Arroba García, Patricia y Moya Fernández, José Manuel (2015). Self-Organizing maps for detecting abnormal thermal behavior in data centers. En: "8th IEEE International Conference on Cloud Computing (CLOUD)", 27/06/2015 - 02/07/2015, New York, EE.UU. pp. 138-145.

Descripción

Título: Self-Organizing maps for detecting abnormal thermal behavior in data centers
Autor/es:
  • Aransay, Ignacio
  • Zapater Sancho, Marina
  • Arroba García, Patricia
  • Moya Fernández, José Manuel
Tipo de Documento: Ponencia en Congreso o Jornada (Artículo)
Título del Evento: 8th IEEE International Conference on Cloud Computing (CLOUD)
Fechas del Evento: 27/06/2015 - 02/07/2015
Lugar del Evento: New York, EE.UU
Título del Libro: 8th IEEE International Conference on Cloud Computing (CLOUD)
Fecha: 2015
Materias:
Palabras Clave Informales: Anomaly detection, data centers, self-organizing maps
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 (267kB) | Vista Previa

Resumen

The increasing success of Cloud Computing applications and online services has contributed to the unsustainability of data center facilities in terms of energy consumption. Higher resource demand has increased the electricity required by computation and cooling resources, leading to power shortages and outages, specially in urban infrastructures. Current energy reduction strategies for Cloud facilities usually disregard the data center topology, the contribution of cooling consumption and the scalability of optimization strategies. Our work tackles the energy challenge by proposing a temperature-aware {VM} allocation policy based on a {Trust-and-Reputation} System ({TRS}). A {TRS} meets the requirements for inherently distributed environments such as data centers, and allows the implementation of autonomous and scalable {VM} allocation techniques. For this purpose, we model the relationships between the different computational entities, synthesizing this information in one single metric. This metric, called reputation, would be used to optimize the allocation of {VMs} in order to reduce energy consumption. We validate our approach with a state-of-the-art Cloud simulator using real Cloud traces. Our results show considerable reduction in energy consumption, reaching up to 46.16\% savings in computing power and 17.38\% savings in cooling, without {QoS} degradation while keeping servers below thermal redlining. Moreover, our results show the limitations of the {PUE} ratio as a metric for energy efficiency. To the best of our knowledge, this paper is the first approach in combining {Trust-and-Reputation} systems with Cloud Computing {VM} allocation.

Proyectos asociados

TipoCódigoAcrónimoResponsableTítulo
Gobierno de EspañaTEC-2012-33892Sin especificarSin especificarTECNOLOGIAS HW/SW PARA LA EFICIENCIA ENERGETICA EN SISTEMAS DE COMPUTACION DISTRIBUIDOS
Gobierno de EspañaRTC-2014-2717-3Sin especificarSin especificar3 OPTIMIZACIÓN ENERGÉTICA DE CENTROS DE DATOS DE INFRAESTRUCTURAS CLOUD BASADAS EN OPENSTACK
Gobierno de EspañaIPT-2012-1041-430000ConTVLABSin especificarConnectedTV Lab (ConTVLAB) SISTEMA DISTRIBUIDO DE VERIFICACIÓN, PRUEBA Y CERTIFICACIÓN DE APLICACIONES Y SERVICIOS DE TELEVISIÓN CONECTADA DE NUEVA GENERACIÓN (HbbTV, Android TV, Smart TV)

Más información

ID de Registro: 42751
Identificador DC: http://oa.upm.es/42751/
Identificador OAI: oai:oa.upm.es:42751
Depositado por: Memoria Investigacion
Depositado el: 04 Sep 2016 07:35
Ultima Modificación: 04 Sep 2016 07:35
  • 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