Presentation | 2021-01-22 A Study of Caching Policy with Cache Hit Prediction for User Generated Video Meguru Yamazaki, Miki Yamamoto, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | With wide deployment of video platforms on which users can upload their generating videos, such as YouTube and niconico, User-Generated Content (UGC) has been attracting a lot of attention. UGC is reported to have different characteristics of popularity from commercial video delivery services such as Netflix and Hulu. Popularity of some UGC has a tendency of short-term temporal variation. This feature degrades the performance of caching methods such as widely deployed LRU. New caching methods taking account of manually analyzed viewing tendency of UGCs have been proposed. Viewing tendencies are generally quite different for platforms, regions and times. It is difficult to respond to these diverse UGC dynamics in these existing proposals because of complexity of manual analysis of viewing tendency and manual tuning of caching strategy. In this paper, we newly propose a machine learning approach for caching policy for UGCs. In our approach, cache hit ratio of the content is predicted and caching policy is designed by using this predicted cache hit ratio. Our performance evaluation results using YouTube traces show that our proposed method can improve cache performance when compared with several conventional approaches. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Cache / UGC / Machine Learning |
Paper # | NS2020-121 |
Date of Issue | 2021-01-14 (NS) |
Conference Information | |
Committee | NS |
---|---|
Conference Date | 2021/1/21(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Online |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Network software (Software architecture, Middleware), Network application, SOA/SDP, NGN/IMS/API, Distributed control/Dynamic routing, Grid, NFV, IoT, Network/System reliability, Network/System evaluation, etc. |
Chair | Akihiro Nakao(Univ. of Tokyo) |
Vice Chair | Tetsuya Oishi(NTT) |
Secretary | Tetsuya Oishi(NTT) |
Assistant | Shinya Kawano(NTT) |
Paper Information | |
Registration To | Technical Committee on Network Systems |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | A Study of Caching Policy with Cache Hit Prediction for User Generated Video |
Sub Title (in English) | |
Keyword(1) | Cache |
Keyword(2) | UGC |
Keyword(3) | Machine Learning |
1st Author's Name | Meguru Yamazaki |
1st Author's Affiliation | Kansai University(Kansai Univ.) |
2nd Author's Name | Miki Yamamoto |
2nd Author's Affiliation | Kansai University(Kansai Univ.) |
Date | 2021-01-22 |
Paper # | NS2020-121 |
Volume (vol) | vol.120 |
Number (no) | NS-327 |
Page | pp.pp.66-69(NS), |
#Pages | 4 |
Date of Issue | 2021-01-14 (NS) |