A Two Time-Scales Network Bandwidth Measurement for Video Transmission
Peng Wang, Guangyuan Zhang, Cui Ni, Kefeng Li · 2016
In order to solve the contradiction between the reliability of video transmission and the network bandwidth fluctuations, a two time-scales network bandwidth measurement for video stream transmission is proposed. Firstly, a model-based long time-scale bandwidth trend extraction is proposed, which is used to calculate the current bandwidth through a Transmission Control Protocol (TCP) throughput model, and predict a trend of network bandwidth using an Exponential Smoothing Model (ESM) according to the calculated current bandwidth. Secondly, short time-scale bandwidth fluctuation detection is proposed to divide the network status into three categories, according to which additively increase or multiplicatively decrease the estimated bandwidth. The experimental results illustrate that our proposed algorithm can satisfy the requirements of TCP-friendliness and real-time for the video transmission.