Get in Touch
 Duration 14 hours

Course Outline

Introduction to AIOps via Open Source Solutions

  • Core concepts and strategic benefits of AIOps.
  • The role of Prometheus and Grafana within the observability stack.
  • Positioning ML in AIOps: distinguishing between predictive and reactive analytics.

Establishing Prometheus and Grafana Environments

  • Installation and configuration of Prometheus for robust time series data collection.
  • Construction of Grafana dashboards utilizing real-time metric streams.
  • Exploration of exporters, relabeling mechanisms, and service discovery patterns.

Preparing Data for Machine Learning

  • Extraction and transformation of raw Prometheus metrics.
  • Curation of datasets optimized for anomaly detection and forecasting tasks.
  • Leveraging Grafana’s native transformation features or Python-based pipelines.

Deploying Machine Learning for Anomaly Detection

  • Implementation of foundational ML models for outlier identification (e.g., Isolation Forest, One-Class SVM).
  • Processes for training and evaluating models against time series data.
  • Integration of anomaly visualizations into Grafana dashboards.

Utilizing ML for Metric Forecasting

  • Development of basic forecasting algorithms (including ARIMA, Prophet, and introductory LSTM concepts).
  • Prediction of system load and resource consumption patterns.
  • Application of forecasts to inform early alerting strategies and scaling decisions.

Connecting ML with Alerting and Automation

  • Formulation of alert rules derived from ML outputs or dynamic thresholds.
  • Management of Alertmanager configurations and notification routing.
  • Automation of workflows and script triggering upon anomaly detection.

Scaling and Productionizing AIOps

  • Integration with external observability ecosystems (e.g., ELK stack, Moogsoft, Dynatrace).
  • Operationalization of ML models within broader observability pipelines.
  • Adherence to best practices for implementing AIOps at enterprise scale.

Course Recap and Future Roadmap

Requirements

  • A solid grasp of system monitoring and observability principles.
  • Practical experience utilizing Grafana or Prometheus.
  • Proficiency in Python and a foundational understanding of machine learning concepts.

Target Audience

  • Observability engineers.
  • Infrastructure and DevOps teams.
  • Monitoring platform architects and Site Reliability Engineers (SREs).

Number of participants


Price per participant

Upcoming Courses

Related Categories