Ashot Harutyunyan

Challenges and Experiences in Designing Interpretable KPI-diagnostics for Cloud Applications

Bio:

Ashot Harutyunyan is an information theorist with a long-term experience in academic and industrial research domains. His works investigate fundamental limits in data transfer and storage, optimal hypothesis testing, and ML applications. Inventor of 70+ US patents in AI operations for automated cloud management.

Description of the Talk:

Automated root cause analysis of performance problems in modern cloud computing infrastructures is of a high technology value in the self-driving context. The talk focuses on diagnosis of cloud ecosystems through their Key Performance Indicators (KPI). Those indicators are utilized to build automatically labeled data sets and train explainable AI models for identifying conditions and processes “responsible” for misbehaviors. Our experiments on a large time series data set from a cloud application demonstrate that those approaches are effective in obtaining models that explain unacceptable KPI behaviors and localize sources of issues.