| Presentation | 2022-05-20 Anomaly Event Classification Method using Observability Data in Autonomous Control Loop Yukitsugu Sasaki, Masaru Sakai, Kensuke Takahashi, Satoshi Kondou, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | An autonomous control loop system has been proposed in which each operation part operates autonomously by making the function of maintenance operation into parts. It monitors the object service, and it aims at realization of autonomous tracking and automatic recovery for addition of new function to the service, specification change and failure generation. In the previous research, the information acquisition method for utilizing observability data called Logs/Metrics/Tracing, etc. has been proposed, but the concrete correspondence method in the failure has not been proposed. In response to failures, observability data can be used and machine learning models such as random forests can be used to operate predetermined functions for failures corresponding to the past. However, machine learning models of supervised learning must be assigned to any failure among failures learned in advance, and it is difficult to operate appropriate workers when anomaly events occur. In this paper, we propose an event classification method at failure occurrence using clustering of unsupervised learning and one-vs-one to judge known and anomaly events. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Autonomous distributed system / Network management / Operation |
| Paper # | ICM2022-9 |
| Date of Issue | 2022-05-12 (ICM) |
| Conference Information | |
| Committee | ICM / IPSJ-CSEC / IPSJ-IOT |
|---|---|
| Conference Date | 2022/5/19(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Kazuhiko Kinoshita(Tokushima Univ.) |
| Vice Chair | Haruo Ooishi(NTT) / Eiji Takahashi(NEC) |
| Secretary | Haruo Ooishi(Bosco) / Eiji Takahashi(Fujitsu) |
| Assistant | Yoshifumi Kato(NTT) |
| Paper Information | |
| Registration To | Technical Committee on Information and Communication Management / Special Interest Group on Computer Security / Special Interest Group on Internet and Operation Technology |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Anomaly Event Classification Method using Observability Data in Autonomous Control Loop |
| Sub Title (in English) | |
| Keyword(1) | Autonomous distributed system |
| Keyword(2) | Network management |
| Keyword(3) | Operation |
| 1st Author's Name | Yukitsugu Sasaki |
| 1st Author's Affiliation | NIPPON TELEGRAPH AND TELEPHONE CORPORATION(NTT) |
| 2nd Author's Name | Masaru Sakai |
| 2nd Author's Affiliation | NIPPON TELEGRAPH AND TELEPHONE CORPORATION(NTT) |
| 3rd Author's Name | Kensuke Takahashi |
| 3rd Author's Affiliation | NIPPON TELEGRAPH AND TELEPHONE CORPORATION(NTT) |
| 4th Author's Name | Satoshi Kondou |
| 4th Author's Affiliation | NIPPON TELEGRAPH AND TELEPHONE CORPORATION(NTT) |
| Date | 2022-05-20 |
| Paper # | ICM2022-9 |
| Volume (vol) | vol.122 |
| Number (no) | ICM-32 |
| Page | pp.pp.42-46(ICM), |
| #Pages | 5 |
| Date of Issue | 2022-05-12 (ICM) |