Open AccessAn Analysis and Proof on Self‐Similarity Property of Flash P2P Internet Video Traffic
Author(s) -
Ji Yimu,
Yuan Yongge,
Han Zhijie,
Wang Hao,
Han Lei,
Sun Yanfei,
Wang Ruchuan
Publication year - 2015
Publication title -
chinese journal of electronics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.267
H-Index - 25
eISSN - 2075-5597
pISSN - 1022-4653
DOI - 10.1049/cje.2015.01.005
Subject(s) - self similarity , computer science , flash (photography) , the internet , interval (graph theory) , internet video , internet traffic , similarity (geometry) , traffic flow (computer networking) , peer to peer , computer network , traffic generation model , property (philosophy) , real time computing , mathematics , artificial intelligence , world wide web , image (mathematics) , art , philosophy , geometry , epistemology , visual arts , combinatorics
In order to study the amount of bandwidthresource loss caused by flash P2P technique, its influenceon network load and its maintenance cost, the characteristicof Internet traffic of flash P2P is studied. On the basisof analysis of features of Real time media flow protocol(RTMFP), the traffic of flash P2P can be identified fromthe Internet traffic. By extraction and analysis of the trafficof the three largest online video content providers inChina (Youku, Iqyi and Sohu Video) and the calculationof probability distribution of the traffic, it is found that thetransmission time of flash P2P traffic and the transmissiontime interval obeys the heavy‐tailed distribution. This accountsfor the self‐similarity of the flash P2P traffic. Tobetter explain the phenomenon, the long‐range dependentmodel is established based on the current traffic. By theestablished mathematical model, it is strictly proved thatflash P2P traffic has self‐similar characteristic.