Everyday IT operators are trying to prevent outages of business-critical applications. When prevention is not possible, IT operators strive to reduce the mean time to repair (MTTR) as much as possible. Improving resolution time can be quite a challenge. But IT operators don't stand alone in this challenge. They can use smart solutions that support Automated Root Cause Analysis and Anomaly Detection.
Get Better Observability With Machine Learning Anomaly Detection. DevOps teams today are challenged with the rapid growth and complexity of infrastructure. Managing those environments only through static thresholds becomes insufficient, so to address this issue, modern DevOps teams rely on advanced ML/AI algorithms.
In this tutorial, we’ll use the BIRCH (balanced iterative reducing and clustering using hierarchies) algorithm from scikit-learn with the ADTK (Anomaly Detection Tool Kit) package to detect anomalous CPU behavior. We’ll use the InfluxDB 2.0 Python Client to query our data in InfluxDB 2.0 and return it as a Pandas DataFrame. This tutorial assumes that you have InfluxDB and Telegraf installed and configured on your local machine to gather CPU stats.
When you want to spot hosts, applications, containers, plant equipment, or sensors that are behaving differently from others, you can use the Median Absolute Deviation (MAD) algorithm to identify when a time series is “deviating from the pack”. In this tutorial, we’ll identify anomalous hosts using mad() — the Flux implementation of MAD — from a Third Party Flux Package called anaisdg/anomalydetection.
Do you still find yourself visually monitoring dashboards for anomalies? That leaves catching revenue-related issues to chance. It’s become humanly impossible to catch incidents on streaming data. This is why many eCommerce and data-driven companies have adopted automated anomaly detection.
Imagine driving on the freeway in a (partially) self-driving car like a Tesla. While you drive the car, you come across things you would expect like trees, lampposts and other cars but also things that don't belong there like trash floating around. Meanwhile, radars and sensors in the car are working hard to make sure you don't crash because of these things. If you see the freeway as your fast-changing IT environment, then all the things that don't belong there are anomalies.
As a company known for our anomaly detection, we know a thing or two about spotting irregularities. So as we reached the end of 2019, we couldn’t help but think back on the 2010s and the anomalies that shook the world. Once we got to listing them, it really became tough to pick just 10. Ultimately, after much debate, we ranked them based on their impact, newsworthiness and how utterly unexpected they were.
As Chief Data Scientist here at StackState I’ve got a big interest in less likely to happen occurrences in data. These events are called anomalies. Every company with a considerable IT environment should be able to detect, solve and also prevent anomalies. Because anomalies can have a big effect on your day to day business.
