Log Clustering Based Problem Identification for Online Service Systems

By Qingwei Lin, Hongyu Zhang, Jian-Guang Lou, Yu Zhang, Xuewei Chen. 2016 IEEE/ACM 38th International Conference on Software Engineering Companion (ICSE-C), 2016

534 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Software

View Paper: https://www.semanticscholar.org/paper/e1a2c4cb9db7f84b051f123e197fd0899e61eec8

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

1. Michael R. Lyu
2. Zibin Zheng
3. Jieming Zhu
4. Yuxin Su
5. Shilin He
6. Pinjia He
7. Tianyi Yang
8. Zhuangbin Chen

In Software

1. Zibin Zheng
2. Michael R. Lyu
3. Jieming Zhu
4. Shilin He
5. Pinjia He

Citations in the corpus

• LogBERT: Log Anomaly Detection via BERT (2021, unknown): “LogCluster [44] employs two training phrases, knowledge base initialization phrase and online learning phrase, to generate clusters.”
• Experience Report: System Log Analysis for Anomaly Detection (2016, methodology): “In this paper, we review and evaluate six anomaly detection methods employing log analysis [12], [15], [26], [27], [28], [47] because of their novelty and representativeness.”
• Tools and Benchmarks for Automated Log Parsing (2018, methodology): “[11] develop a clustering algorithm to group similar issues.”
• A Survey on Automated Log Analysis for Reliability Engineering (2020, background): “To tackle the challenge of pattern change caused by system upgrades, several studies [46, 108] supported online update of a previously trained model to adapt to unprecedented log patterns.”
• DeepLog: Anomaly Detection and Diagnosis from System Logs through Deep Learning (2017, unknown): “Besides workƒows, other systems that perform anomaly diagnosis using system logs include DISTALYZER [26] that diagnoses system performance issues by comparing a problematic log against a normal one, LogCluster [19] which clusters and organizes historical logs to help future problem identi€cation, an”