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.
Abstract
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.
关键词
流媒体 /
对等计算 /
协议分析 /
特征提取 /
流量优化
{{custom_keyword}} /
Key words
flow media /
FLASH P2P /
protocol analysis /
feature extraction /
traffic
optimization
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1]THORNBURGH M. Adobe′s secure realtime media flow protocol draftthornburghadobe
rtmfp09[EB/OL]. (2013-06-28)[2015-10-08].http:∥tools.ietf.org/html/draft-
thornburgh-adobe-rtmfp-09.
[2]鲁刚,张宏莉,叶麟. P2P流量识别[J]. 软件学报,2011,22(6): 1281-1298.
LU G,ZHANG H L,YE L. P2P traffic identification [J]. Journal of Software,2011,22(6):
1281-1298.(in Chinese)
[3]杨楷,汪斌强,张震. 基于多特征的P2P直播流识别方法[J]. 电子技术应用,2014,40(2): 125-
127.
YANG K,WANG B Q,ZHANG Z. A method of identifying P2P live streaming based on union
features[J]. Computer Technology and Its Applications,2014,40(2): 125-127. (in Chinese)
[4]单凯,高仲合,禹继国. 基于节点及流量行为特征的P2P流量识别[J]. 济南大学学报(自然科学版
),2014,28(4):265-269.
SHAN K,GAO Z H,YU J G. Identification of P2P flow based on node and traffic behavior
characteristics[J]. Journal of University of Jinan (Sci & Tech),2014,28(4):265-269. (in
Chinese)
[5]钱亚冠,张旻. 基于过抽样技术的P2P流量识别方法[J]. 电信科学,2014,30(4):109-113.
QIAN Y G,ZHANG M. P2P traffic identification based oversampling technique [J].
Telecommunications Science,2014,30(4):109-113. (in Chinese)
[6]李致远,王汝传. 一种基于机器学习的P2P网络流量识别方法[J]. 计算机研究与发展,2013,48
(12): 2253-2260.
LI Z Y,WANG R C. A P2P network traffic identification approach based on machine learning[
J]. Journal of Computer Research and Development,2013,48 (12): 2253-2260. (in Chinese)
[7]YE W,CHO K. Hybrid P2P traffic classification with heuristic rules and machine
learning[J]. Soft Computing,2014,18(9): 1815-1827.
[8]ZHANG G Q,TANG M D,CHENG S Q,et al. P2P traffic optimization[J]. Science China:
Information Sciences,2012,55(7):1475-1492.
[9]涂睿,苏金树. 一种基于Hash的位置标识映射机制[J]. 计算机工程与科学,2010,30(2):70-74.
TU R,SU J S. A hashbased locator/ID mapping mechanism[J]. Computer Engineering &
Science,2010,30(2):70-74.(in Chinese)
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
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)
{{custom_fund}}