A smart packet type identification scheme for selective discard of video packets

Abstract

In recent years, due to the growth of social networks and development of video sharing platforms, transmission of video content has increased dramatically. This huge amount of data imposes a heavy load on the limited bandwidth of the networks. As a result, data loss will be inevitable. Nevertheless, since some types of video frames, such as B-frames are more resilient to packet loss, discarding them can ease network congestion while maintaining QoE. However, frame-type information is only available in the packet payload. Limited processing power of devices in high-speed networks, data encryption and user credibility issues, make finding the frame types a costly operation. Therefore, an intelligent router with fast and reliable decision-making is proposed to model live video streams structures and recognize the importance of video packets at the network level. This information enables the network routers to discard insignificant video packets ahead of congestion. The proposed method does not need to read the IP layer payload and uses only the packet header data for decision making. Experimental results show an intelligent router, at the worst scenario can classify packet type with better than 95.1% accuracy, as if packet types are marked at the source without any bias. Tests on various HD video, with 1–10% packet drop rates, shows while the proposed packet discarding scheme is 0.8–2.7 dB inferior to ground truth method, it is still 6–10 dB better than dropping packets at random.