In this paper, we discuss the concept of multia4gent systems as applied to high-speed network traffic control. In the high-speed domain, the propagation delay in a network causes significant problems. One of them is that any centralized control is too late to maintain normal network operations, so distributed tra~c control by autonomous agents is required. The basic idea of our traffic control for high-speed networks is a combination of distributed local control and centralized global control; that is, bcfore the global control becomes effective, Ml network nodes try to maintain their operations in cooperation with other nodes. The significance of propagation delay in such networks requires that the communication delay is included in the model of the node ~gents. This paper proposes a multiagent traffic control and illustrates the experimental results. The results show that the control based on the multiagent system can improve the efficiency of network control.
[1]
Victor Lesser,et al.
Multistage negotiation in distributed planning
,
1988
.
[2]
Mark Klein,et al.
Supporting conflict resolution in cooperative design systems
,
1991,
IEEE Trans. Syst. Man Cybern..
[3]
Raj Jain,et al.
Congestion control with explicit rate indication
,
1995,
Proceedings IEEE International Conference on Communications ICC '95.
[4]
Debasis Mitra,et al.
Optimal design of windows for high speed data networks
,
1990,
Proceedings. IEEE INFOCOM '90: Ninth Annual Joint Conference of the IEEE Computer and Communications Societies@m_The Multiple Facets of Integration.
[5]
Giampiero Pecelli,et al.
Dynamic behavior of feedback congestion control schemes
,
1995,
Proceedings of INFOCOM'95.
[6]
Alan H. Bond,et al.
Readings in Distributed Artificial Intelligence
,
1988
.