A neural-net based fuzzy connection admission controller for wireless ATM

A neural-net based fuzzy connection admission controller for a wireless ATM network is designed. It is a QoS-guaranteed controller, where QoSs of both the air interface and ATM network are taken into consideration. Hence, for the neural fuzzy admission decision controller, we further design a fuzzy capacity requirement estimator, fuzzy air interface performance estimator, and a fuzzy system status estimator for reflecting the equivalent capacity required by the new call request, air interface performance, and the ATM network status, respectively. The simulation result shows that the neural fuzzy connection admission controller can gain high bandwidth utilization for wireless ATM networks.