Broadband integrated networks
Quality of service: delivering QoS on the Internet and in corporate networks
Quality of service: delivering QoS on the Internet and in corporate networks
Design of a VLSI fuzzy processor for ATM traffic sources management
LCN '95 Proceedings of the 20th Annual IEEE Conference on Local Computer Networks
Intelligent Control Techniques for Efficient Regulation of ABR Queue Length in ATM Switches
ISCC '97 Proceedings of the 2nd IEEE Symposium on Computers and Communications (ISCC '97)
Effective control of traffic flow in ATM networks using fuzzy explicit rate marking (FERM)
IEEE Journal on Selected Areas in Communications
Hi-index | 0.00 |
This paper studies the problems of congestion and optimal use of resources in packet switched backbone networks. The developed control system adjusts the data rates and selects the optimal paths through the backbone network for the controllable traffic category. Controllable traffic is low priority traffic, whose sources can be effectively controlled by the network. Data rates of the controllable traffic are calculated by the fuzzy controllers and statistical calculations. The adaptive neuro-fuzzy inference system (ANFIS) has been used to predict data rates of high priority traffic. This prediction tries to optimise the performance of the control system. All computationally intensive control operations are distributed to the edge switches of the backbone network. A special control protocol transfers the control information between the edge switches and the source stations of the controllable traffic, located in the access networks. Simulation tests have been used to verify the high performance of the control system.