Prediction-Based Dynamic Load Balancing Using Agent Migration for Multi-agent System

Multi-agent system in the ubiquitous computing environment can provide customized services to the users by effectively utilizing the distributed resources. The existing dynamic load balancing approach invokes the migration of agents even for temporal imbalance of the loads. In this paper we propose a prediction-based dynamic load balancing scheme which can effectively avoid unnecessary agent migration. An experiment reveals that the proposed approach significantly reduces the service response time compared with the existing scheme. It enables the agent system to quickly adapt to the environment change through effective load balancing.

[1]  S.D.J. McArthur,et al.  Multi-Agent Systems for Power Engineering Applications—Part II: Technologies, Standards, and Tools for Building Multi-agent Systems , 2007, IEEE Transactions on Power Systems.

[2]  Hee Yong Youn,et al.  A Dynamic Weighting Scheme for Providing Fair Communication Service to Nomadic Agents , 2008, 2008 Eighth International Conference on Intelligent Systems Design and Applications.

[3]  Hee Yong Youn,et al.  A New Agent Platform Architecture Supporting the Agent Group Paradigm for Multi-Agent Systems , 2007 .

[4]  Hee Yong Youn,et al.  Hierarchical P2P Networking and Two-Level Compression Scheme for Multi-agent System Supporting Context-Aware Applications , 2008, 2008 Eighth International Conference on Intelligent Systems Design and Applications.

[5]  Jiannong Cao,et al.  Scalable load balancing on distributed web servers using mobile agents , 2003, J. Parallel Distributed Comput..

[6]  Nicolas Lhuillier,et al.  FOUNDATION FOR INTELLIGENT PHYSICAL AGENTS , 2003 .

[7]  Hee Yong Youn,et al.  An Efficient Dynamic Load Balancing Scheme for Multi-agent System Reflecting Agent Workload , 2009, 2009 International Conference on Computational Science and Engineering.

[8]  Hee Yong Youn,et al.  Priority-Based Message Scheduling for the Multi-agent System in Ubiquitous Environment , 2007, 2007 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology - Workshops.