Performance Anomaly Detection - Computer Measurement Group
Observability Virtual Conference – Q&A Report from Slack
June 1, 2020
Computer Performance Modeling
June 3, 2020

Performance Anomaly Detection

The Power of Control Charts: How to Use Them, Read Them, and Build Them

In this course designed by performance and capacity expert Dr. Igor Trubin, learners will participate in lectures and hands-on activities to become familiar with:

  • Machine learning based Anomaly Detection techniques
  • Classical (SPC) and MASF (For system performance data) Control Charting
  • Control Chart use
  • Types of Control Charts
  • Reading, building, and interpreting Control Charts
  • Typical cases of real-world issues captured by an anomaly detection system – VMs, Mainframes, Middleware, E2E response, and more
  • How to build free AWS cloud server with R and build Control Charts
  • Performance anomaly (Perfomaly) detection system R implementation example (SEDS-lite—open source-based tool)

Course Syllabus

  • Performance Anomaly Detection – concept
  • Detecting Performance Anomalies (“Perfomalies”) by Control Charts
  • Detecting Performalies by IT-Charts
  • Setting up Free AWS Public Cloud EC2 Server with R-Studio to Develop and Run Simple Performaly Detection Programs
  • Practice 1: Examples and Exercises (using Spreadsheet)
  • Practice 2: Examples and Exercises (using R on AWS cloud)
  • Final Consideration – Build your Own Performaly Detection System!
  • Quiz

Fees: $0 for Members, $149 for Non-Members

Time to Complete: Appx 5 hours

Certificate/Digital Badge: Yes, a Certificate of Completion will be issued.

This course is FREE to CMG annual members. Log in to access the course.

Verified by MonsterInsights