Fuzzy performance management of IEEE 802.4 token bus networks

This paper focuses on performance management of computer communication networks serving large-scale integrated systems. The performance management aims to improve the network performance in handling various types of messages by on-line adjustment of protocol parameters. The principle of fuzzy logic have been used in formulating the performance management rules and in deriving management decisions. This fuzzy performance management has been evaluated with an IEEE 802.4 network that is simulated by a discrete event simulation language. The results of this paper offer a step forward to bridging the gap between management standards and users' demands for efficient network operations since most standards address only the architecture, services, and interfaces for network management. Moreover, the results shows that the fuzzy performance management procedure is much simpler than the one previously developed with perturbation analysis, stochastic approximation, and learning automata.