Radial basis functions for bandwidth estimation in ATM networks using RBF neural network

It is known that some types of variable bit rate (VBR) video traffic exhibit strong long term correlations and non-stationary behavior. Estimation of an accurate amount of bandwidth to support this traffic has been a challenge task using conventional algorithmic approaches. In this paper, we show that a radial basis function neural networks (RBFNN) is capable of learning the non-linear multi-dimentional mapping between different video traffic patterns, quality of service (QoS) requirements and the required bandwidth to support each call. In addition, RBFNN model adopts to new traffic senarios and still produces accurate results. This approach bypass the modeling approach which requires detailed knowledege about the traffic statistical patterns. Our method employes "on-line" measurments of the traffic count process over a monitoring period. In order to simplify the designe of the RBFNN, the input traffic is preprocessed through a lowpass filter in order to smooth all high fluctations. A large set of data, representing different patterns with different QoS requirements, was used to ensure that RBFNN can generalize and produce accurate results when confronted with new data. The reported results prove that the neurocomputing approach is effective in achieving more than other traditional upon mathematical or simulation analysis. This is primiarly due to the fact that the unique learning and adaptive capabilities of NN enable them to extract and memorize rules from previous experience.