A Space-Based Generic Pattern for Self-Initiative Load Balancing Agents

  • Authors:
  • Eva Kühn;Vesna Sesum-Cavic

  • Affiliations:
  • Institute for Computer Languages Space Based Computing Group, Vienna University of Technology, Wien, Austria 1040;Institute for Computer Languages Space Based Computing Group, Vienna University of Technology, Wien, Austria 1040

  • Venue:
  • ESAW '09 Proceedings of the 10th International Workshop on Engineering Societies in the Agents World X
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

Load-Balancing is a significant problem in heterogeneous distributed systems. There exist many load balancing algorithms, however, most approaches are very problem specific oriented and a comparison is therefore complex. This paper proposes a generic architectural pattern for a load balancing framework that allows for the plugging of different load balancing algorithms, reaching from unintelligent to intelligent ones, to ease the selection of the best algorithm for a certain problem scenario. As in complex network environments there is no "one-fits-all solution", also the integration of several different algorithms shall be supported. The presented pattern assumes autonomous agents and decentralized control. It can be composed towards arbitrary network topologies, foresees exchangeable policies for load-balancing, and uses a black-board based communication mechanism to achieve high software architecture agility. The pattern has been implemented and first instantiations of it with three algorithms have been benchmarked.