SAPS: Significance-Aware Packet Scheduling for Real-Time Streaming of Layer Encoded Video

In this paper, we propose a novel packet scheduling algorithm for real-time streaming of layer encoded video. In real-time streaming of layer encoded video, application needs to select subset of compressed information so that it does not overflow the available network bandwidth nor limited client queue depth. We use greedy approach based upon "packet significance" in selecting packets. We develop a notion of packet significance which elaborately captures the importance of a packet over user perceivable QoS. Packet significance incorporates video semantics of a packet, i.e. I, P or B frame type, inter-layer and inter-frame dependency structure of layer encoded video. We apply packet significance weighted scheduling in determining the transmission schedule of selected packets. We perform experiment using publicly available MPEG-4 video traces. Our scheduling algorithm brings significant improvement on user perceivable QoS.