| Presentation | 2023-03-02 Performance Evaluation of D2D Caching Method Using LSTM Makoto Tsunekiyo, Noriaki Kamiyama, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | As video viewing on mobile terminals becomes more common, there is concern that the backhaul traffic load on cellular networks (CN) will increase dramatically. To reduce the backhaul load, mobile edge computing, which distributes video content from a cache at the base station, has been attracting attention, but another effective method to further reduce the load is to cache the content at the mobile terminal and distribute it via D2D（device-to-device）communication. However, since the cache capacity of the MT is limited, it is effective to preferentially cache content that is expected to be in high demand along the MT's route of travel. Therefore, we proposed content demand estimation using deep learning to D2D cache delivery. We proposed a method to select contents to be cached on MTs by estimating contents that were likely to be demanded by other MTs on the travel route using a long-short term memory (LSTM) neural network, which was one of the algorithms of deep learning. First, we generated time-series data based on the number of keyword searches (number of viewings) for 10 well-known movie titles to confirm the effectiveness of the demand estimation part of the proposed method and the generality of the learning model. Next, a cache was created by making delivery requests based on the pre-movement demand distribution using the predicted values, and the hit rate with the content in the cache was calculated when delivery requests were made based on the post-movement demand distribution. Then, we compared the total number of requests per content measured and predicted for California (CA) and New York (NY) in the U.S. with the cache hit rate of LRU and the proposed method, and we confirmed that high-demand content can be predicted at the destination where the MT moved. In this paper, to reflect more realistic environment, the cache hit rate is evaluated with and without considering the popularity bias of the content used in the simulation, and when the number of content is increased. The effectiveness of the proposed method is confirmed. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | D2D / LSTM / cache |
| Paper # | NS2022-175 |
| Date of Issue | 2023-02-23 (NS) |
| Conference Information | |
| Committee | IN / NS |
|---|---|
| Conference Date | 2023/3/2(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Okinawa Convention Centre + Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | General |
| Chair | Kunio Hato(Internet Multifeed) / Tetsuya Oishi(NTT) |
| Vice Chair | Tsutomu Murase(Nagoya Univ.) / Takumi Miyoshi(Shibaura Insti of Tech.) |
| Secretary | Tsutomu Murase(KDDI Research) / Takumi Miyoshi(Nagaoka Univ. of Tech.) |
| Assistant | / Kotaro Mihara(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) | Performance Evaluation of D2D Caching Method Using LSTM |
| Sub Title (in English) | |
| Keyword(1) | D2D |
| Keyword(2) | LSTM |
| Keyword(3) | cache |
| 1st Author's Name | Makoto Tsunekiyo |
| 1st Author's Affiliation | Fukuoka University(Fukuoka Univ.) |
| 2nd Author's Name | Noriaki Kamiyama |
| 2nd Author's Affiliation | Ritsumeikan University(Ritsumeikan Univ.) |
| Date | 2023-03-02 |
| Paper # | NS2022-175 |
| Volume (vol) | vol.122 |
| Number (no) | NS-406 |
| Page | pp.pp.47-52(NS), |
| #Pages | 6 |
| Date of Issue | 2023-02-23 (NS) |