Path selection using available bandwidth estimation in overlay-based video streaming

IP networks present a challenging environment for video streaming because they do not provide throughput, jitter, or loss rate guarantees. In this work, we focus on improving the perceived quality of video streaming through dynamic path selection. Selecting one of several Internet paths is possible using multihoming and/or an overlay routing infrastructure. We conduct an experimental comparison of various measurement-based path selection techniques for video streaming. The path selection is based on the measurement of network-layer metrics, such as loss rate, jitter or available bandwidth, while the video quality is evaluated based on the VQM tool. Our experiments show that the most effective technique for adaptive path selection relies on an estimate of the lower bound of the available bandwidth variation range. We show how to perform such measurements using the video packets, eliminating the measurement overhead in the selected path. Finally, we show that adaptive path selection is more effective than a simple, but commonly used, form of FEC.