| Presentation | 2021-03-19 Proposal of Anomaly Cause Analysis Method Based on Operation Status and Operation Log of Virtualization Infrastructure Junichi Higuchi, Takeshi Kodama, Hirokatsu Jo, Hitoshi Ueno, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In recent years, IT virtualization infrastructure is used as the foundation of cloud services that are widely spread. In the current operation of the virtualization infrastructure, there is a problem that the recovery time of the abnormality becomes longer because the operator investigates the cause and copes with it after the abnormality that affects the cloud users occurs. Therefore, in order to cope with the abnormality before it occurs, we are investigating an approach to detect the unusual behavior of the virtualization infrastructure early and to determine the cause. One method of determining the cause in the actual operation is to check the event recorded in the operation log for the abnormal time and place and determine whether the event is a possible cause. In the method, there is a problem that the event of the cause candidate can’t be narrowed down when the occurrence place and time of the cause is not known from the abnormal detection place and time. In this paper, we propose a method to extract events of cause candidates by narrowing down the places and periods of suspected causes based on the detailed occurrences of unusual behavior. As a result of the evaluation of the proposed method, we confirmed that the proposed method can extract the cause event in two cases where the cause occurrence place and time are not known from the abnormal detection place and time. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Virtualization Infrastructure / Operation Log / Anomaly Detection / Root Cause Analysis |
| Paper # | ICM2020-72 |
| 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) | Proposal of Anomaly Cause Analysis Method Based on Operation Status and Operation Log of Virtualization Infrastructure |
| Sub Title (in English) | |
| Keyword(1) | Virtualization Infrastructure |
| Keyword(2) | Operation Log |
| Keyword(3) | Anomaly Detection |
| Keyword(4) | Root Cause Analysis |
| 1st Author's Name | Junichi Higuchi |
| 1st Author's Affiliation | ITSU LABORATORIES LTD.(FUJITSU LAB.) |
| 2nd Author's Name | Takeshi Kodama |
| 2nd Author's Affiliation | ITSU LABORATORIES LTD.(FUJITSU LAB.) |
| 3rd Author's Name | Hirokatsu Jo |
| 3rd Author's Affiliation | Fujitsu Kyushu Network Technologies Limited(QNET) |
| 4th Author's Name | Hitoshi Ueno |
| 4th Author's Affiliation | ITSU LABORATORIES LTD.(FUJITSU LAB.) |
| Date | 2021-03-19 |
| Paper # | ICM2020-72 |
| Volume (vol) | vol.120 |
| Number (no) | ICM-433 |
| Page | pp.pp.70-75(ICM), |
| #Pages | 6 |
| Date of Issue | 2021-03-11 (ICM) |