Answers are grounded in this paper and cite their sources.
By using the server push of the hypertext transfer pro-tocol (HTTP) version 2.0, i.e., HTTP/2, along with the technique of server pacing, a novel scheme is proposed in this paper to deliver video segments. Furthermore, the load of bitrate adaptation is shifted to the server to avoid bandwidth competition and wastage caused by bitrate switching. It can be explicitly shown that no significant overhead is brought by our proposed scheme via complexity analysis. Moreover, our proposed scheme generates one HTTP request only. With extensive simulations, we successfully demonstrate that it is superior over the closely related schemes in terms of the average achievable bitrate, the number of buffer stalls, the ratio of unclaimed pushes, etc., in particular, when a harsh network condition arises.
No takes yet. Share an insight, caveat, or question.
Ferng et al. (2021) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: