Age of AI Ops
summary
Covers AIOps—using machine learning and data analytics to automate real-time responses across infrastructure and software—by describing its key attributes, the technology layers involved, and the specific problems AIOps aims to address with case studies. Presents a reference architecture for AIOps and discusses future directions. Technologies implied include ML-driven analytics applied to monitoring and incident response across distributed infrastructure and software stacks.
AI-written summary · about
chapters (12)
- 0:00Start
- 3:33Check Out Transaction Configuration
- 4:24Check Out Transaction Troubleshooting
- 8:10Current Focus Areas Anomaly Detection, Root Cause Analysis, Autonomous Action
- 9:22Contextual Anomaly Detection Model
- 13:51Integrated Architecture
- 17:00Anomaly Detection & RCA Workflow
- 18:44Looking Forward
- 20:28Clustering KPI to find performance outliers
- 20:52Clustering metadata to find mis-configured nodes
- 21:28Snapshot analysis to identify bottleneck methods
- 23:02The Central Nervous System
related talks
19mAIOps
30mIntelligent Analysis on Cloud Infrastructure With AIOps
02mAIOPS – How can machine learning help in IT operations
29mAIOps Is How We Will Survive DevOps
05mLightning Talk: AIOps vs. MLOps: What's the Difference?
24mAI Ops and its challenges
24mFrom DevOps to MLOps: Enabling Artificial Intelligence
20mAutomated Incident Management