摘要
基于互联网视频流量日夜增多和服务质量得不到保障的问题,提出一种FLASH P2P流量识别模型和优化方案.从FLASH P2P协议原理、特征提取和流量优化等方面进行了深入研究,并结合优酷、爱奇艺、搜狐视频等视频网站使用FLASH P2P协议交互和应用效果,重点分析每个网站是如何实现FLASH P2P协议部署他们的视频服务器,以及在部署服务器时,如何设计和解决流量优化问题.通过抓包试验进行分析,研究结果表明:提出的分析方法流量识别率高,流量优化方案可以解决视频网站中存在的流量本地化不足问题,从而可以提高用户体验,并为互联网视频公司节约了带宽支付成本.
To solve the problems that the internet video traffic was increased day by day and the service quality was not guaranteed, a FLASH P2P traffic identification model and optimization scheme were proposed to improve the utilization of network bandwidth resources. FLASH P2P protocol principle, feature extraction and traffic optimization were studied deeply, and the applying effects were analyzed for three major domestic video websites of Youku, Aqiyi and Sohu Video by FLASH P2P protocol interaction. The methods of deploying the video server with FLASH P2P protocol and designing the deployed server to solve optimization problem were specially analyzed. The capturing experiment analysis results show that the proposed analysis method can recognize the flow rate efficiently, and the flow optimization scheme can solve the problem of inadequate video site in the presence of flow localization. The user experience can be improved, and the cost of bandwidth in Internet video company can be decreased.
出处
《江苏大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2016年第5期585-590,共6页
Journal of Jiangsu University：Natural Science Edition
基金
江苏省基础研究计划青年基金资助项目(BK20130876)
南京信息职业技术学院科研基金资助项目(YK20140402)
江苏省未来网络项目(BY2013095-4-03)
关键词
流媒体
对等计算
协议分析
特征提取
流量优化
flow media
FLASH P2P
protocol analysis
feature extraction
traffic optimization
