Presentation | 2021-03-19 Evaluation of automatic generation method of network failure point estimation rule Fumika Asai, Norio Yamamoto, Shunsuke Kanai, Haruhisa Nozue, Kenichi Tayama, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | It is important to identify the suspected failure point quickly in order to realize the early restoration in the failure response work of a large-scale network. So far, we have proposed a technique to automatically create If-then rules to estimate the failure point by using failure response history and event information (Trap information and alarms) of monitoring system as training data. Our technique realizes to specify the failure point independently of skill and know-how of the maintenance person. However, existing methods focus only on events that occur in the device, so if there are rules generated for failures that occur in fewer types of events than other failures, multiple failures may be detected in addition to true failure, and the failure type may not be identified as one. Therefore, the failure may not be identified, and further isolation may be required. In this paper, by considering events that did not occur in comparison with other failure classification, we propose an automatic generation technique of If-then rules with negative conditions for events that did not occur, and show its superiority and applicability to actual operation. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Network / Estimation of Network Failure Point / Automatic Rule Generation |
Paper # | ICM2020-67 |
Date of Issue | 2021-03-11 (ICM) |
Conference Information | |
Committee | ICM |
---|---|
Conference Date | 2021/3/18(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Online |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Kazuhiko Kinoshita(Tokushima Univ.) |
Vice Chair | Yoichi Sato(OSL) / Haruo Ooishi(NTT) |
Secretary | Yoichi Sato(NTT) / Haruo Ooishi(Bosco) |
Assistant | Tetsuya Uchiumi(Fujitsu Lab.) |
Paper Information | |
Registration To | Technical Committee on Information and Communication Management |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Evaluation of automatic generation method of network failure point estimation rule |
Sub Title (in English) | |
Keyword(1) | Network |
Keyword(2) | Estimation of Network Failure Point |
Keyword(3) | Automatic Rule Generation |
1st Author's Name | Fumika Asai |
1st Author's Affiliation | Nippon Telegraph and Telephone Corporation(NTT) |
2nd Author's Name | Norio Yamamoto |
2nd Author's Affiliation | Nippon Telegraph and Telephone Corporation(NTT) |
3rd Author's Name | Shunsuke Kanai |
3rd Author's Affiliation | Nippon Telegraph and Telephone Corporation(NTT) |
4th Author's Name | Haruhisa Nozue |
4th Author's Affiliation | Nippon Telegraph and Telephone Corporation(NTT) |
5th Author's Name | Kenichi Tayama |
5th Author's Affiliation | Nippon Telegraph and Telephone Corporation(NTT) |
Date | 2021-03-19 |
Paper # | ICM2020-67 |
Volume (vol) | vol.120 |
Number (no) | ICM-433 |
Page | pp.pp.42-47(ICM), |
#Pages | 6 |
Date of Issue | 2021-03-11 (ICM) |