Adaptive available bandwidth estimation for internet video streaming

In this study, an adaptive available bandwidth estimation approach that is suitable for Internet video streaming is developed. The algorithm exploits repetitive measurements and uses this redundancy to improve its video adaptation decision. The importance of available bandwidth estimation in Internet applications has recently increased particularly because of the heterogeneity of the network links. Many of the Internet paths may contain wired and wireless links in which loss may happen due to congestion as well as link errors. Hence, loss rate by itself is not a sufficient statistics for monitoring purposes. If the loss is due to congestion, video quality can then be decreased whereas if the loss is due to link error, no such action is necessary. Moreover, in video streaming, such an estimate can be used to determine the new video rate if the quality is to be increased. In our approach, active probing packets are used to estimate bandwidth in very short time duration. The novelty of our estimator is its adaptivity in the sense that the overhead caused by the estimator is automatically reduced when congestion builds up. The trade off is reduced accuracy. Such accuracy is not needed under congestion anyway and when things get back to normal, our estimator turns back to normal operation mode. We have integrated our algorithm into our video streamer and carried out experiments on both simulated and actual streaming applications on the Internet. The results indicate that our estimator algorithm increases streaming performance substantially.