Multi-ressources K-Médians: un algorithme de placement de services web sur les réseaux sans fils municipaux

Authors:
Julien Gossa;Nipaul Long
Affiliations:
INSA de Lyon - LIRIS UMR, Villeurbanne, France;Institut de Technologie du Cambodge, Phnom Penh, Cambodge
Venue:
UbiMob '08 Proceedings of the 4th French-speaking conference on Mobility and ubiquity computing
Year:
2008

Citing 7
Cited 0

The Ninja architecture for robust Internet-scale systems and services373423

Computer Networks: The International Journal of Computer and Telecommunications Networking - pervasive computing
Partitionable Services: A Framework for Seamlessly Adapting Distributed Applications to Heterogeneous Environments

HPDC '02 Proceedings of the 11th IEEE International Symposium on High Performance Distributed Computing
Replica placement in adaptive content distribution networks

Proceedings of the 2004 ACM symposium on Applied computing
Optimal Resource-Aware Deployment Planning for Component-Based Distributed Applications

HPDC '04 Proceedings of the 13th IEEE International Symposium on High Performance Distributed Computing
Dynamic placement for clustered web applications

Proceedings of the 15th international conference on World Wide Web
Solution methods for the p-median problem: An annotated bibliography

Networks
Grid'5000: A Large Scale and Highly Reconfigurable Grid Experimental Testbed

GRID '05 Proceedings of the 6th IEEE/ACM International Workshop on Grid Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Nowadays, numerous municipalities are laying free wireless Internet access infrastructures on. These infrastructures are a natural target for the deployment of Web services, such as mapping or multimedia content providing. Regarding the number of clients, ensuring their performances represents one particularly important challenge. Unfortunately, this challenge is hard because of Web services peculiarities: difficult to migrate and replicate, heterogeneous, and highly interdependent. Our proposal is an algorithm designed to build deployment plans for sets of Web services, according to their interdependency while ensuring performances and load balancing. We have shown the efficiency of this algorithm, called MRKM for Multi-Resources K-Median, on the Grid 5000 experimental platform.