VBR video traffic management using a predictor-based architecture

The efficient transportation of real-time Variable Bit Rate (VBR) video tra ffic in the high-speed networks has been an area of active research. An imp ortant issue is the simplicity with which the bandwidth allocation and sche duling schemes can be executed online with realtime constraints in the futu re high-speed networks. The correlation properties of the VER video traffic make the predictor-based online traffic adaptation techniques attractive. We developed a novel predictor-based dynamic bandwidth allocation (PDBA) sc heme for short-term resource management and studied its queuing performance . In order to reduce the effects of the prediction errors on the queuing sy stem and hence the underutilization of reserved bandwidth, a novel short-te rm controller (STC) that works at the cell-level has been introduced and th e system has been called the PDBA-STC system. This online VER video traffic prediction-based traffic management scheme has low complexity and is suita ble for implementation in high-speed networks Ranganathan et al. [N. Rangan athan, R, Anand, G, Chiruvolu, A VLSI ATM architecture for VER traffic, Pro c. IEEE International Conference on VLSI Design, 1998, pp. 420-427] and has been demonstrated to provide better performance than other existing simple schemes. This paper also investigates the predictability of VER video traf fic that exhibits long-range dependence (LRD) based on a fractional ARIMA ( 1,d,0) model, The short-range dependent (SRD) Auto Regressive (AR) model fo r prediction of VER video traffic has also been considered for evaluation o f the proposed dynamic bandwidth allocation scheme and the performance has been compared to that of LRD-based prediction Finally, a summary and future research have been discussed, (C) 2000 Elsevier Science B.V. All rights re served.