Fuzzy backward congestion notification (FBCN) congestion control in asynchronous transfer mode (ATM) networks

We study the performance of a fuzzy control scheme as a first step to develop better control strategies for avoiding congestion and attaining high link utilisation in ATM based networks. Due to the complexity of ATM networks and the many parameters involved, explicit modeling of their dynamic behaviour is very difficult if not impossible. On the other hand, for systems which are difficult to obtain analytical models for, approximate models developed by using fuzzy logic based techniques are being applied successfully. We summarize our investigation on the suitability of fuzzy logic control techniques to solve difficult ATM network control problems. As a part of our ongoing research, we describe and report the performance of the fuzzy backward congestion notification (FBCN) method to support best effort service such as the available bit rate (ABR) service in ATM based networks.