Alarm Correlation Method Using Bayesian Network in Telecommunications Networks
-
- Yuya HATA
- NTT Network Innovation Center, NTT Corporation
-
- Naoki HAYASHI
- NTT Network Innovation Center, NTT Corporation
-
- Yusuke MAKINO
- NTT Network Innovation Center, NTT Corporation
-
- Atsushi TAKADA
- NTT Network Innovation Center, NTT Corporation
-
- Kyoko YAMAGOE
- NTT Network Innovation Center, NTT Corporation
書誌事項
- 公開日
- 2022-09-28
- DOI
-
- 10.34385/proc.70.ps2-01
- 公開者
- The Institute of Electronics, Information and Communication Engineers
説明
In the operation of information technology services, operators monitor the equipment-issued alarms, to locate the cause of a failure and take action. Alarms generate simultaneously from multiple devices with physical/logical connections. Therefore, if the time and location of the alarms are close to each other, it can be judged that the alarms are likely to be caused by the same event. In this paper, we propose a method that takes a novel approach by correlating alarms considering event units using a Bayesian network based on alarm generation time, generation place, and alarm type. The topology information becomes a critical decision element when doing the alarm correlation. However, topology information updates manually when the failures or construction, errors in the topology information may occur. Therefore, by taking into location information other than topology information, we show that event-by-event correlation with 100% accuracy is possible even if the topology information is 25% wrong.
収録刊行物
-
- IEICE Proceeding Series
-
IEICE Proceeding Series 70 PS2-01-, 2022-09-28
The Institute of Electronics, Information and Communication Engineers
- Tweet
詳細情報 詳細情報について
-
- CRID
- 1390575506739299072
-
- ISSN
- 21885079
-
- 本文言語コード
- en
-
- データソース種別
-
- JaLC
-
- 抄録ライセンスフラグ
- 使用不可