earticle

영어

With the widespread penetration of broadband accesses, many multimedia applications, such as video surveillance, on-demand video streaming, IPTV and news broadcast are emerging. Since video streaming applications on the Internet generally have very high bandwidth requirements and yet are often unresponsive to network congestion. In order to avoid congestion collapse and improve video quality, these applications need to respond to congestion in the network by deploying adaptive control mechanisms. In this paper, we present a receiver-based, bandwidth estimation rate control mechanism with content-aware probability retransmission to limit the burden on the congested network. Like the TCP Friendly Rate Control (TFRC) protocol, we compute the sending rate as a function of the loss event rate and round-trip time. Considering the different importance of three distinct types of frames in Standard MPEG encoders, we divide data packets into three grades coarsely and adopt adaptive probability retransmission strategy to assure video playback quality. It is an extension of TCP friendly congestion control. This paper describes the smooth rate algorithm and probability retransmission mechanism. The result of experiments with competing TFRC specification demonstrates the proposed approach reaches a higher throughput and higher PSNR than TFRC congestion control algorithms especially on the bottleneck links.