Application of fuzzy logic for estimation of equivalent capacity in high-speed networks

The dynamic nature of high-speed networks poses difficult traffic control problems when trying to achieve efficient use of network resources. To cope with rapidly changing network conditions, traffic control methods for high-speed networks must be adaptive, flexible and intelligent for efficient network management. The use of intelligent methods based on fuzzy logic, neural networks and genetic algorithms can prove to be efficient for such traffic control. In this paper, we propose a fuzzy equivalent capacity estimator for bandwidth allocation in high-speed networks. Performance evaluation via simulation shows that the proposed fuzzy estimator has a good equivalent capacity estimation compared with fluid flow and stationary approximations.