Y. Won, Y. Jeon, J. Jeong, I. Jang, and S. Hong (Korea)
Multi-Resolution, Video Streaming, QoS, Packet Schedul ing, Traffic Smoothing
In this work1 , we propose novel packet scheduling algo rithm for real-time streaming of multi-resolution video. Our scheduling algorithm targets towards the situation where there exists relatively large fluctuation in bandwidth availability and the short queue depth in the receiver’s end. The proposed algorithm determines which packets to send and when to send them. We develop QoS significance met ric to represent the importance of a packet. QoS signifi cance incorporates the composite transitive dependency in multi-resolution video. We develop QoS weighted traf fic smoothing to determine the transmission schedule. We found that when the receiver has short queue length, e.g. mobile terminal, packet loss is very sensitive to the packet interval distribution. In determining the packet transmis sion schedule, we consider not only the bandwidth process of the packet traffic but also the importance of the indi vidual packets. We introduce more slack for more impor tant packet. We found that QoS weighted traffic smoothing makes the resulting bandwidth process burstier and entails more packet losses. However, it greatly enhances the user perceivable QoS. The simulation results show that the our scheme not only maximizes user perceivable QoS but also minimizes resource requirements.
Important Links:
Go Back
