Outlier Detection is now available as part of the Grafana Machine Learning toolkit in Grafana Cloud for Pro and Advanced users. With this feature, you can monitor a group of similar things, such as load-balanced pods in Kubernetes, and get alerted when some of them start behaving differently than their peers. There’s supposed to be a video here, but for some reason there isn’t. Either we entered the id wrong (oops!), or Vimeo is down.

Companies today are relying on technology more than ever thanks to widespread digital transformation and cloud initiatives. And this is increasing the need for safe, efficient and reliable IT environments. But maintaining operational IT stability is very difficult when considering the complex and dynamic nature of today’s IT environments. In fact, IT environments are constantly changing, with new network devices, users and software versions coming into existence.

This article was originally published in The New Stack and is reposted here with permission. Hundreds of billions of sensors produce vast amounts of time series data every day. The sheer volume of data that companies collect makes it challenging to analyze and glean insights. Machine learning drastically accelerates time series data analysis so that companies can understand and act on their time series data to drive significant innovation and improvements.

In this blog, we examine how anomaly detection helps by setting up healthy alerts and providing efficient root cause analysis. Anomaly detection, part of AIOps, guides your attention to the places and times where remarkable things occurred. It reduces information overload, thereby speeding up RCA investigation.

Modern Kubernetes environments are becoming increasingly complex. In 2021, Datadog analyzed real-world usage data from more than 1.5 billion containers and found that the average number of pods per organization had doubled over the course of two years. Organizations running containers also tend to deploy more monitors than companies that don’t leverage containers, pointing to the increased need for monitoring in these environments.

Anomaly detection can be defined by data points or events that deviate away from its normal behavior. If you think of this in the context of time-series continuous datasets, the normal or expected value is going to be the baseline, and the limits around it represent the tolerance associated with the variance. If a new value deviates above or below these limits, then that data point can be considered anomalous.

A month ago, we introduced unsupervised ML & Anomaly Detection in Netdata, the Anomaly Advisor. Today, we’re happy to announce that we’re bringing anomaly rates to every chart in Netdata Cloud. Anomaly information is no longer limited to the Anomalies tab and will be accessible to you from the Overview and Single Node View tabs as well. This will make your troubleshooting journey easier, as you will have the anomaly rates for any metric available with a single click.

Wouldn’t it be great to peek into the future and find answers to the problems that you’re facing today? This may sound like science fiction, but many companies currently possess this capability, and they are creating strategies around it to strengthen their monitoring and analytical capabilities. One way is time series forecasting, a statistical method. You can take advantage of the insights of time series forecasting by using techniques like anomaly detection to gain.