论文部分内容阅读
移动终端有限的处理能力和无线带宽制约了高清视频应用的进一步发展.针对这一问题,提出基于Docker的混合云视频直播体系,减少直播流传输时延、转码开销和传输成本.该直播体系利用私有云的可定制性降低直播流初始转码的时延.同时,设计转码通道工作量预测模型、延迟预测模型和直播流分发算法.利用公有云弹性可扩展、分布范围广的特点,考虑多个移动终端转码通道重叠的部分,减少直播流转码开销和在多个数据中心之间传输时的成本.实验结果表明,该直播体系有效减少了直播流传输时延,转码开销和传输成本.
The limited processing power and wireless bandwidth of the mobile terminal have restricted the further development of HD video applications.Aiming at this problem, this paper proposes a hybrid cloud video live broadcast system based on Docker to reduce the transmission delay, transcoding overhead and transmission cost of live streaming. The private cloud customization can reduce the delay of the initial transcoding of the live streaming.At the same time, design the transcoding channel workload prediction model, the delay prediction model and the live streaming distribution algorithm.Using the public cloud elasticity scalable and distributed a wide range of features, Considering the overlapping parts of transcoding channels of multiple mobile terminals, the transcoding overhead of live streaming and the cost of transmitting between multiple data centers are reduced.The experimental results show that the live broadcast system can effectively reduce the transmission delay, transcoding overhead and Transmission costs.