For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Stability and Adaptability of Autonomous Decentralized Flow Control in High-Speed Networks
Chisa TAKANO Masaki AIDA
IEICE TRANSACTIONS on Communications
Publication Date: 2003/10/01
Print ISSN: 0916-8516
Type of Manuscript: Special Section PAPER (IEICE/IEEE Joint Special Issue on Assurance Systems and Networks)
Category: Network Control and Management
autonomous decentralized system, flow control, diffusion, feedback,
Full Text: PDF>>
This paper focuses on flow control in high-speed networks. Each node in a network handles its local traffic flow on the basis of only the information it is aware of, but it is preferable that the decision-making of each node leads to high performance of the whole network. To this end, we investigate the relationship between the flow control mechanism of each node and network performance. We consider the situation in which the capacity of a link in the network is changed but individual nodes are not aware of this. Then we investigate the stability and adaptability of the network performance, and discuss an appropriate flow control model on the basis of simulation results.