Improving the Communication Performance in Multi-Agent Systems for Distributed Manufacturing Process Control

The distributed control of complex and dynamic manufacturing systems is a challenging task and the multi-agent system (MAS) becomes a suitable solution due to its flexibility in both distributing and integrating software functionalities across the controlled system. This paper investigates the potentials of improving agent message delivery by enhancing the underlying communication network with IP QoS mechanisms using service differentiation and early congestion avoidance techniques. The extensive simulation experiments demonstrated the effectiveness of our approach in providing small latency, small jitter and improved throughputs in ACL message delivery, whilst without deteriorating other data applications between distributed controllers.

[1]  Jon Crowcroft,et al.  Congestion control mechanisms and the best effort service model , 2001, IEEE Netw..

[2]  S.D.J. McArthur,et al.  Exploiting Multi-agent System Technology within an Autonomous Regional Active Network Management System , 2007, 2007 International Conference on Intelligent Systems Applications to Power Systems.

[3]  Edward Curry,et al.  A JMS Message Transport Protocol for the JADE platform , 2003, IEEE/WIC International Conference on Intelligent Agent Technology, 2003. IAT 2003..

[4]  Biplab Sikdar,et al.  Scalable configuration of RED queue parameters , 2001, 2001 IEEE Workshop on High Performance Switching and Routing (IEEE Cat. No.01TH8552).

[5]  Lisa Cingiser DiPippo,et al.  A real-time multi-agent system architecture for e-commerce applications , 2001, Proceedings 5th International Symposium on Autonomous Decentralized Systems.

[6]  Donald Steiner,et al.  FIPA: Foundation for Intelligent Physical Agents - Das aktuelle Schlagwort , 1998, Künstliche Intell..

[7]  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.