Log Anomaly to Resolution: AI Based Proactive Incident Remediation

• Published in: IEEE/ACM International Conference on Automated Software Engineering : [proceedings] pp. 1353 - 1357
• Main Authors: Mahindru, Ruchi, Kumar, Harshit, Bansal, Sahil
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.11.2021
• Subjects: aiops; Artificial intelligence; cloud; Documentation; incident triage; log anomaly detection; Metadata; Middleware; Production; Servers; Signal resolution

Based on 2020 SRE report, 80% of SREs work on postmortem analysis of incidents due to lack of provided information and 16% of toil come from investigating false positives/negatives. As a cloud service provider, the desire is to proactively identify signals that can help reduce outages and/or reduce...