Presentation | 2019-03-05 Characteristic Analysis of P2PTV Traffic and Its Classification Using Machine Learning Koji Hayashi, Takumi Miyoshi, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Peer-to-peer video streaming service (P2PTV) has attracted attention due to the huge demands for video streaming services. Since the user terminals (peers) share data, it is possible to distribute the load concentration on the server in P2PTV. However, P2PTV traffic is difficult to control and manage statically as both the number of peers sharing video data and the throughput vary with respect to each content. A method to classify and model P2PTV traffic by focusing on the number of peers and throughput has been studied. However, the classification criteria are ambiguous, and there is no reproducibility in this study because the authors tried to subjectively classify P2PTV traffic. Clustering, one of machine learning methods, can classify a large amount of data into some categories by calculating the similarity based on the characteristic values of input data. This paper proposes a P2PTV traffic classification method using machine learning. We examined the features extracted by analyzing the characteristics of traffic and then classified traffic data by the clustering method in PPStream and PPTV, typical P2PTV applications. In the characteristics analysis, we examined 18 kinds of features extracted from P2PTV traffic that was obtained when we watched video contents. The classification results in each application show that about 400 P2PTV traffic data sets can be categorized into four clusters. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | P2P / P2PTV / Traffic analysis / Machine learning / Clustering |
Paper # | NS2018-230 |
Date of Issue | 2019-02-25 (NS) |
Conference Information | |
Committee | IN / NS |
---|---|
Conference Date | 2019/3/4(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Okinawa Convention Center |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | General |
Chair | Takuji Kishida(NTT-AT) / Yoshikatsu Okazaki(NTT) |
Vice Chair | Kenji Ishida(Hiroshima City Univ.) / Akihiro Nakao(Univ. of Tokyo) |
Secretary | Kenji Ishida(KDDI Research) / Akihiro Nakao(KDDI Research) |
Assistant | / Kenichi Kashibuchi(NTT) |
Paper Information | |
Registration To | Technical Committee on Information Networks / Technical Committee on Network Systems |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Characteristic Analysis of P2PTV Traffic and Its Classification Using Machine Learning |
Sub Title (in English) | |
Keyword(1) | P2P |
Keyword(2) | P2PTV |
Keyword(3) | Traffic analysis |
Keyword(4) | Machine learning |
Keyword(5) | Clustering |
1st Author's Name | Koji Hayashi |
1st Author's Affiliation | Shibaura Institute of Technology(Shibaura Inst. Tech.) |
2nd Author's Name | Takumi Miyoshi |
2nd Author's Affiliation | Shibaura Institute of Technology(Shibaura Inst. Tech.) |
Date | 2019-03-05 |
Paper # | NS2018-230 |
Volume (vol) | vol.118 |
Number (no) | NS-465 |
Page | pp.pp.219-224(NS), |
#Pages | 6 |
Date of Issue | 2019-02-25 (NS) |