Integration of ATM call admission control and link capacity control by distributed neural networks

An adaptive link capacity control method which uses the adaptive nature of a neural network to estimate call loss rate from observed traffic and link capacity is discussed. Link capacity assignment is optimized by a random optimization method according to the estimated call loss rate. The integration of adaptive call admission control and adaptive link capacity control is shown to yield all efficient asynchronous transfer mode (ATM) traffic control system suitable for multimedia communication services with unknown traffic characteristics. Preliminary computer simulation results of the method are presented