DevConf.US 2020 is the 3rd annual, free, Red Hat sponsored technology conference for community project and professional contributors to Free and Open Source technologies coming to a web browser near you!
Monitoring with Prometheus is becoming a common pattern for cloud native applications. But knowing what metrics to record and how to find relevance is a challenging task. How can AI-based solutions help us automate the process of identifying and alerting when metrics behave differently and also augment human introspection? In this workshop you will learn how to interact with Prometheus metrics and train a machine learning model to perform time series forecasting for detecting potential anomalies. We will walk you through the process of deploying and operating all the tools required to develop your own anomaly detection framework. You will walk away from this workshop knowing how to: 1. Setup a sample web application to generate metrics 2. Configure Prometheus to collect the metrics and Grafana to visualize the metrics 3. Use Python to transform metrics into a suitable format 4. Train a machine learning model to perform time series forecasting
Video Stream
