User-Classified Dynamic Resource Allocation for Real-Time VBR Video Transmission Based on Time-Domain Traffic Prediction

In this paper, a practical dynamic resource allocation scheme for real-time variable bit rate (VBR) video transmission is investigated. This scheme uses time-domain adaptive linear prediction, instead of the conventional size prediction of I-, P- and B- frames, to forecast future bandwidth requirement in time. Media delivery index (MDI) is used here as QoS measurement and complementary reference for adjustment. Besides, considering that the practical multi-user application may arouse adjustment collision, an adjustment priorities classified strategy based on the user-level classifications is put forward. Last, a test-bed based on the proposed scheme is constructed and the experimental results show that the bandwidth effective utilization has increased by 20%-60% compared to a fixed service rate with QoS guaranteed and no collisions.