ANN Based Forecasting of VBR Video Traffic for Dynamic Bandwidth Allocation in ATM Networks

Two time delay neural network (TDNN) based forecasting systems are proposed to perform dynamic bandwidth reservation for real-time, variable bit rate (VBR) video service in ATM networks. Both multilayered perceptron (MLP) and pi-sigma network (PSN) based systems are found to give highly reliable predictions even in a nonstationary environment. Their performance is quantified through simulation experiments on clippings from the movie, "Star Wars". In particular, the PSN-TDNN based dynamic bandwidth reservation achieves high network utilization, loss-free transmission and reasonable delay, and its lower computational requirements make it suitable for on-line operation. keywords: ATM network, real-time VBR video, dynamic bandwidth allocation, time delay neural network, pi-sigma network, forecasting. 1 Introduction Future broadband integrated services digital networks (B-ISDN) will support a wide range of services including voice, data, video and other modalities in an integrated and un..