CBay : Extending auction algorithm for component placement in the Internet of machines

Charbel El Kaed 1, 2 François-Gaël Ottogalli 3 Yves Denneulin 1
1 MESCAL - Middleware efficiently scalable
Inria Grenoble - Rhône-Alpes, LIG - Laboratoire d'Informatique de Grenoble
2 Laboratoire d'Informatique de Grenoble
LIG - Laboratoire d'Informatique de Grenoble
Abstract : The Internet of machines is a system composed of interconnected nodes that inter-operate to run applications. Such applications can be implemented by the encapsulation and the cooperation of several software entities called components. These components are distributed on nodes with various resources (memory, computation capacity, bandwidth, battery charge, etc). Placing components on nodes is a crucial step for both the application and the target machines. The choice of placement actually influences their performance. Hence, the deployment has to take into account the needs and the functional/non functional properties along with the system's available resources and its overall performance. Many algorithms have been proposed, including one based on a principle of auction: DecAp, which allows components' dynamic redeployment to better meet the system's evolution. We present in this article an extension of DecAp by adding the management of available resources (memory, bandwidth and computing capacity) to the redeployment strategy.
Type de document :
Communication dans un congrès
PerCom Workshops, 2010, Manheim, Germany. IEEE, pp.480-485, 2010, 〈10.1109/PERCOMW.2010.5470623〉
Liste complète des métadonnées

https://hal.inria.fr/hal-00788858
Contributeur : Arnaud Legrand <>
Soumis le : vendredi 15 février 2013 - 13:09:35
Dernière modification le : jeudi 11 janvier 2018 - 06:26:38

Identifiants

Collections

Citation

Charbel El Kaed, François-Gaël Ottogalli, Yves Denneulin. CBay : Extending auction algorithm for component placement in the Internet of machines. PerCom Workshops, 2010, Manheim, Germany. IEEE, pp.480-485, 2010, 〈10.1109/PERCOMW.2010.5470623〉. 〈hal-00788858〉

Partager

Métriques

Consultations de la notice

162