THE USE OF LEARNING ALGORITHMS IN ATM NETWORKS CALL ADMISSION CONTROL PROBLEM: A METHODOLOGY

摘要

The Call Admission Control (CAC) problem, one of the most fundamental in ATM networks, has not been solved yet. In this study, we use a novel Stochustic Estimator Learning Algorithm (SELA) to predict in "real lime" if a call request should be accepted or not, for various types of traffic sources. The feedback the algorithm receives has been drawn from the efficient "equivalent bandwidth" approximation proposed in [1]. The proposed scheme exhibits a remarkable statistical gain compared with other CAC schemes reported in the literature, without QOS deterioration. This paper contains a simulation study of its performance and discusses several possible ways in which this work could be extended.