Self-organising Management Overlays for Future Internet Services

  • Authors:
  • Lawrence Cheng;Alex Galis;Bertrand Mathieu;Kerry Jean;Roel Ocampo;Lefteris Mamatas;Javier Rubio-Loyola;Joan Serrat;Andreas Berl;Hermann Meer;Steven Davy;Zeinab Movahedi;Laurent Lefevre

  • Affiliations:
  • University College London, UK;University College London, UK;France Telecom, France;University College London, UK;University College London, UK and University of the Philippines, Philippines;University College London, UK;Universitat Politècnica de Catalunya, Spain;Universitat Politècnica de Catalunya, Spain;University of Passau, Germany;University of Passau, Germany;Waterford Institute of Technology, Ireland;Université Pierre et Marie Curie, France;INRIA RESO, University of Lyon, France

  • Venue:
  • MACE '08 Proceedings of the 3rd IEEE international workshop on Modelling Autonomic Communications Environments
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

Networks are becoming service-aware implying that all relevant business goals pertaining to a service are fulfilled, and also the network resources are used optimally. Future Internet Networks (FIN) have time varying topology (e.g. such networks are envisaged in Autonomic Internet [1], FIND program [2], GENI program [3], FIRE program [4], Ambient Networks [5], Ad-hoc networks [6]) and service availability and service context change as nodes join and leave the networks. In this paper we propose and evaluate a new self-organising service management system that manages such changes known as the Overlay Management Backbones (OMBs). The OMB is a self-organising solution to the problem space in which each OMB node is dynamically assigned a different service context task. The selection of OMB nodes is conducted automatically, without the need of relatively heavy-weighted dynamic negotiations. Our solution relies on the scalability and dynamicity advantages of Distributed Hash Tables (DHTs). This system is needed to select continuously, automatically, and dynamically a set of network nodes, to become responsible for collecting the availability information of service context in the changing network. This solution advances the state of the art avoiding dynamic negotiations between all network nodes reducing management complexity and cost for bandwidth-limited environments.