A Two-Layer Architecture for Failure Prediction Based on High-Dimension Monitoring Sequences
In recent years, the distributed architecture has been widely adopted by security companies with the rapid expansion of their business. A distributed system is comprised of many computing nodes of different components which are connected by high-speed communication networks. With the increasing func...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-01-01
|
| Series: | Complexity |
| Online Access: | http://dx.doi.org/10.1155/2021/6623666 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832547619395600384 |
|---|---|
| author | Xue Wang Fan Liu Yixin Feng Jiabao Zhao |
| author_facet | Xue Wang Fan Liu Yixin Feng Jiabao Zhao |
| author_sort | Xue Wang |
| collection | DOAJ |
| description | In recent years, the distributed architecture has been widely adopted by security companies with the rapid expansion of their business. A distributed system is comprised of many computing nodes of different components which are connected by high-speed communication networks. With the increasing functionality and complexity of the systems, failures of nodes are inevitable which may result in considerable loss. In order to identify anomalies of the possible failures and enable DevOps engineers to operate in advance, this paper proposes a two-layer prediction architecture based on the monitoring sequences of nodes status. Generally speaking, in the first layer, we make use of EXPoSE anomaly detection technique to derive anomaly scores in constant time which are then used as input data for ensemble learning in the second layer. Experiments are conducted on the data provided by one of the largest security companies, and the results demonstrate the predictability of the proposed approach. |
| format | Article |
| id | doaj-art-17f094ac49e04b73878c2cc0bc764d30 |
| institution | Kabale University |
| issn | 1076-2787 1099-0526 |
| language | English |
| publishDate | 2021-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Complexity |
| spelling | doaj-art-17f094ac49e04b73878c2cc0bc764d302025-02-03T06:43:55ZengWileyComplexity1076-27871099-05262021-01-01202110.1155/2021/66236666623666A Two-Layer Architecture for Failure Prediction Based on High-Dimension Monitoring SequencesXue Wang0Fan Liu1Yixin Feng2Jiabao Zhao3School of Management & Engineering, Nanjing University, Nanjing, ChinaSchool of Management & Engineering, Nanjing University, Nanjing, ChinaGuotai Junan Securities, Shanghai, ChinaDepartment of Control and Systems Engineering, Nanjing University, Nanjing, ChinaIn recent years, the distributed architecture has been widely adopted by security companies with the rapid expansion of their business. A distributed system is comprised of many computing nodes of different components which are connected by high-speed communication networks. With the increasing functionality and complexity of the systems, failures of nodes are inevitable which may result in considerable loss. In order to identify anomalies of the possible failures and enable DevOps engineers to operate in advance, this paper proposes a two-layer prediction architecture based on the monitoring sequences of nodes status. Generally speaking, in the first layer, we make use of EXPoSE anomaly detection technique to derive anomaly scores in constant time which are then used as input data for ensemble learning in the second layer. Experiments are conducted on the data provided by one of the largest security companies, and the results demonstrate the predictability of the proposed approach.http://dx.doi.org/10.1155/2021/6623666 |
| spellingShingle | Xue Wang Fan Liu Yixin Feng Jiabao Zhao A Two-Layer Architecture for Failure Prediction Based on High-Dimension Monitoring Sequences Complexity |
| title | A Two-Layer Architecture for Failure Prediction Based on High-Dimension Monitoring Sequences |
| title_full | A Two-Layer Architecture for Failure Prediction Based on High-Dimension Monitoring Sequences |
| title_fullStr | A Two-Layer Architecture for Failure Prediction Based on High-Dimension Monitoring Sequences |
| title_full_unstemmed | A Two-Layer Architecture for Failure Prediction Based on High-Dimension Monitoring Sequences |
| title_short | A Two-Layer Architecture for Failure Prediction Based on High-Dimension Monitoring Sequences |
| title_sort | two layer architecture for failure prediction based on high dimension monitoring sequences |
| url | http://dx.doi.org/10.1155/2021/6623666 |
| work_keys_str_mv | AT xuewang atwolayerarchitectureforfailurepredictionbasedonhighdimensionmonitoringsequences AT fanliu atwolayerarchitectureforfailurepredictionbasedonhighdimensionmonitoringsequences AT yixinfeng atwolayerarchitectureforfailurepredictionbasedonhighdimensionmonitoringsequences AT jiabaozhao atwolayerarchitectureforfailurepredictionbasedonhighdimensionmonitoringsequences AT xuewang twolayerarchitectureforfailurepredictionbasedonhighdimensionmonitoringsequences AT fanliu twolayerarchitectureforfailurepredictionbasedonhighdimensionmonitoringsequences AT yixinfeng twolayerarchitectureforfailurepredictionbasedonhighdimensionmonitoringsequences AT jiabaozhao twolayerarchitectureforfailurepredictionbasedonhighdimensionmonitoringsequences |