| Presentation | 2020-08-04 Continuous Extension of Distributed Graph Management and General Replication Factor Yoichi Ozaki, Kunitake Kaneko, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Replication Factor (RF) and Edge Cut (EC) are known as values that characterize the graph partitioning policy in centralized distributed graph processing. RF is the average number of replicated vertices when managing edges as a key, and EC is the ratio of cut edges to all when managing vertices as a key. Each of them shows the degree of overlap of the partitioned graph data when the graph data is saved in a distributed manner, and the concept is essentially the same. On the other hand, there is no index for redundant storage of graph data in autonomous decentralized graph management in which graph management using either vertices or branches as a key cannot be realized. Therefore, we propose an index, General Replication Factor (GRF). GRF is an extension of RF and EC. It is a sum of the average number of replications of vertices when managing edges and vertices as keys. Through GRF, centralized distributed graph management can be taken as an extreme example of autonomous decentralized graph management. As an evaluation, we simulated distributed autonomous graph management for a graph of 100,000 vertices and 32.79 million edges by changing the mixture ratio and sum of servers. It was confirmed that when the mixture ratio of servers was 50%, GRF increased in the power as the number of servers increased. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Autonomous distributed system / Autonomous distributed graph / Distributed graph management / Distributed graph processing |
| Paper # | IN2020-20 |
| Date of Issue | 2020-07-27 (IN) |
| Conference Information | |
| Committee | IN / CCS |
|---|---|
| Conference Date | 2020/8/3(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Network Science, Future Network, Cloud/SDN/Virtualization, Contents Delivery/Contents Exchange, and others |
| Chair | Kenji Ishida(Hiroshima City Univ.) / Shigeki Shiokawa(Kanagawa Inst. of Tech.) |
| Vice Chair | Kunio Hato(INTERNET MULTIFEED CO.) / Tetsuya Asai(Hokkaido Univ.) / Megumi Akai(Hokkaido Univ.) |
| Secretary | Kunio Hato(Hiroshima City Univ.) / Tetsuya Asai(KDDI Research) / Megumi Akai(NTT) |
| Assistant | / Hidehiro Nakano(Tokyo City Univ.) / Hiroyasu Ando(Tsukuba Univ.) / Takashi Matsubara(Kobe Univ.) / Kosuke Sanada(Mie Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Information Networks / Technical Committee on Complex Communication Sciences |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Continuous Extension of Distributed Graph Management and General Replication Factor |
| Sub Title (in English) | |
| Keyword(1) | Autonomous distributed system |
| Keyword(2) | Autonomous distributed graph |
| Keyword(3) | Distributed graph management |
| Keyword(4) | Distributed graph processing |
| 1st Author's Name | Yoichi Ozaki |
| 1st Author's Affiliation | Keio University(Keio Univ.) |
| 2nd Author's Name | Kunitake Kaneko |
| 2nd Author's Affiliation | Keio University(Keio Univ.) |
| Date | 2020-08-04 |
| Paper # | IN2020-20 |
| Volume (vol) | vol.120 |
| Number (no) | IN-125 |
| Page | pp.pp.65-70(IN), |
| #Pages | 6 |
| Date of Issue | 2020-07-27 (IN) |