多优先级的异构网络多路径并行视频传输算法

为了在异构网络环境中使用多路径高效的并行传输高质量的视频流，本文针对H.264视频编码中不同的图像帧丢失后对解码造成的不同影响，提出了一种多优先级的多路径并行视频分配算法。所提出的算法将不同图像帧分成两个优先级，并根据整个网络的实时状态动态的把视频流分配到不同的路径中，使得系统在接收端丢失最少的图像帧。仿真结果表明，所提出的算法可以大大减少网络的丢帧率，提升网络传输视频数据性能。 

Multi Priority Concurrent Multipath Transfer for Video Streaming in Heterogeneous Wireless Networks

In order to support a high-quality video streaming in heterogeneous wireless network and minimize the number of missing image frames in receiver side, a multi priority concurrent multipath transfer algorithm for video streaming was proposed in this paper. The proposed algorithm use Lyapunov Optimization to model the network and divided three kinds of image frame in H.264 into two different priority by the different effects caused by their loss, calculating the probability of timeout frame drop in each path and allocated the video streaming into different paths based on the real-time network state. The simulation results show that the proposed algorithm can greatly reduce the image frames loss rate to enhance the performance of the video streaming in heterogeneous wireless network. At the same time, it is proved that the proposed algorithm can ensure the network stability, and support most video stream service.