An Artificial Neural Network Approach for Mechanisms of Call Admission Control in UMTS 3G Networks

CAC-RD (call admission control based on reservation and diagnosis) [1] is call admission control (CAC) for UMTS (universal mobile terrestrial system) 3G networks. It is based on two schemes: channel reservation and network diagnosis. When compared to other CAC mechanisms, CAC-RD can guarantee network availability, reducing priority classes blocking and guarantying some network QoS requirements. Due to computational resource limits, simulations cannot answer related to admission control in big networks with thousands of users. This work presents a method to extrapolate scientific questions like CAC´s behavior with thousands of users and many antennas. An artificial neural network (ANN) approach for CAC-RD in UMTS 3G networks is presented. Its main goal is ANN training with the CAC-RD behavior. It is expected that the ANN can answer questions related to real cellular 3G networks admission control.