| Presentation | 2020-05-15 Progressive Slicing : Practical Application Classification System for Application Slicing Takamitsu Iwai, Akihiro Nakao, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | With the proliferation of encrypted traffic and the increasing importance of application-specific QoE management, the need for application identification is increasing. However, existing research on application identification do not discuss the impact of slice allocation errors due to misclassification and the decrease in QoE due to delays of classification. In this paper, we propose a new architecture called Progressive Slicing, which adaptively allocates the flow into slices with high bandwidth according to the state and result of the classification. The QoE can be maintained by allocating a small bandwidth to the new flow and adaptively transitioning it to a slice with a larger bandwidth according to the classification results. In addition, by performing multiple classifications, we can assign the flows to the slices according to each result, making slicing more tolerant of misclassification and maintaining the QoE of the application. In the proposed system, we evaluate the influence in QoE for multiple user scenarios and the amount of data consumed during the decision making on the Android VM and show that this method can reduce the search time in Twitter by 18% compared to the case where this method was not implemented. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Machine Learning / Application Identification / Network Slicing |
| Paper # | NS2020-17 |
| Date of Issue | 2020-05-07 (NS) |
| Conference Information | |
| Committee | NS |
|---|---|
| Conference Date | 2020/5/14(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Doshisha University |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | High level protocol, Networking technologies (IP and high-layer routing/filtering, Multicast, Quality/Routing control), IP network application technologies (P2P, P4P, Overlay, SIP, NGN), Network system related technologies (System configuration, Interface, Architecture, Hardware/Software/Middleware), Security, Blockchain etc. |
| Chair | Yoshikatsu Okazaki(NTT) |
| Vice Chair | Akihiro Nakao(Univ. of Tokyo) |
| Secretary | Akihiro Nakao(Osaka Pref Univ.) |
| 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) | Progressive Slicing : Practical Application Classification System for Application Slicing |
| Sub Title (in English) | |
| Keyword(1) | Machine Learning |
| Keyword(2) | Application Identification |
| Keyword(3) | Network Slicing |
| 1st Author's Name | Takamitsu Iwai |
| 1st Author's Affiliation | University of Tokyo(UTokyo) |
| 2nd Author's Name | Akihiro Nakao |
| 2nd Author's Affiliation | University of Tokyo(UTokyo) |
| Date | 2020-05-15 |
| Paper # | NS2020-17 |
| Volume (vol) | vol.120 |
| Number (no) | NS-19 |
| Page | pp.pp.57-62(NS), |
| #Pages | 6 |
| Date of Issue | 2020-05-07 (NS) |