A video stream scheduling method and scheduling system based on in-band network telemetry

Abstract

The invention discloses a video stream scheduling method and scheduling system based on in-band network telemetry. The method uses the in-band telemetry technology to carry fine-grained network information to a server. Stream scheduling, and reduce the bit rate of the video stream in time when the network is congested, so as to reduce the usage of network resources. The invention solves the problem that the traditional client self-adaptive video stream algorithm requests excessively high-quality video due to inaccurate estimation of network conditions, reduces the usage of network resources, and improves the experience quality of users watching videos.

Description

technical field [0001] The invention relates to in-band network telemetry technology, in particular to a video stream scheduling method and scheduling system based on in-band network telemetry. Background technique [0002] Video traffic accounts for a large share of the Internet, with video-on-demand streaming accounting for a major portion. The number of network users is increasing but the network resources are very limited. Therefore, how to allocate the limited network resources to multiple devices more reasonably to maintain the fairness of the user experience and avoid the abuse of network resources has become a difficult point in video streaming research. User viewing experience while reducing total network overhead as much as possible. Among them, the video bit rate adaptive algorithm is a method that can adaptively select the encoding rate of the video according to the network conditions estimated by the client to adjust the video quality, and is widely used in the...

AI Technical Summary

Problems solved by technology

[0003] However, there are certain problems in the actual deployment of the bit rate adaptive algorithm: the client estimates the network status by downloading the quality of several consecutive video blocks or by detecting the amount of video content stored in the buffer to judge the current network status

The time required for this is too much delay for the ever-changing network, which is very unfavorable for the decision-making of the video bit rate adaptive algorithm. It may overestimate the network situation and choose a higher bit rate, resulting in network congestion and unnecessary resource overhead, and even make the video unable to download in time and freeze

Images