Figures of the Article
-
Snapshot of alarm log data, log sequence, and log template data[7]. (a) Original log entry: detailed packet exchange information. (b) Processed log data with structured format. (c) Sequences of log events highlighting the anomaly detection process. (d) Regular expressions used for log parsing and anomaly identification. (e) Tabular representation of log sequences with corresponding block IDs and labels.
-
Flow chart of APRGAN.
-
Structure of APRGAN. (a) Rule miner of APRGAN and the pretraining process of APRGAN. (b) Structure of GAN in APRGAN and the data generation process of APRGAN.
-
Dynamic update mechanism based on the category distribution difference.
-
Comparison of the BLEU scores of alarm log data generated by different parameter values.
-
Comparison of the ROUGE-L scores for (a) HDFS and (b) OpenStack alarm log data generated by different algorithms.
-
Comparison of the METEOR scores for (a) HDFS and (b) OpenStack alarm log data generated by different algorithms.
-
Comparison of fault detection results achieved by the DeepLog models trained on data augmented by different algorithms and original data (HDFS logs).
-
Comparison of fault detection results achieved by the DeepLog models trained on data augmented by different algorithms and original data (OpenStack logs).
-
Comparison of the precision of the root cause diagnosis (HDFS logs).
-
Comparison of the precision of the root cause diagnosis (OpenStack logs).
Others
-
External link to attachment
https://rdcu.be/dUUBa -
PDF format
2024-4-13-2408-Highlights 452KB
Related articles
-
2025, 40(2): 397-412. DOI: 10.1007/s11390-024-3337-8
-
2025, 40(2): 359-377. DOI: 10.1007/s11390-024-3661-z
-
2024, 39(6): 1269-1280. DOI: 10.1007/s11390-023-2638-7
-
2024, 39(1): 177-191. DOI: 10.1007/s11390-023-2256-4
-
2021, 36(1): 207-220. DOI: 10.1007/s11390-020-9713-0
-
2020, 35(4): 794-808. DOI: 10.1007/s11390-020-0314-8
-
2020, 35(2): 259-267. DOI: 10.1007/s11390-020-9969-4
-
2019, 34(6): 1217-1229. DOI: 10.1007/s11390-019-1971-3
-
2019, 34(1): 47-60. DOI: 10.1007/s11390-019-1898-8
-
2018, 33(3): 511-521. DOI: 10.1007/s11390-018-1835-2