A new neuro-fuzzy system for efficient ATM traffic control
J.J. Custodio · 1999
We present and apply the fuzzy adaptive system ART-based (FasArt) neuro-fuzzy system to the problems of connection admission control (CAC) and usage parameter control (UPC). FasArt provides the advantages of both a fuzzy logic system (simplicity and interpretability of fuzzy rules) and an ART-based neural network (fast, stable and incremental learning). An extensive experimental work in the Ptolemy simulation environment is presented, together with an analysis of system performance. Besides the general fine properties of FasArt, a superior performance was confirmed in comparison to other conventional, fuzzy or neural systems in the UPC problem, with respect to selectiveness, low response time and false alarm probability. On the other hand, performance in the CAC problem was satisfactory, as far as cell loss rate and link usage are concerned, especially when FasArt was employed as a function identification system.