Advanced alerting with Grafana Machine Learning
Advanced alerting with Grafana Machine Learning
This event has concluded
A recording will be available soon. Sign up to be alerted.
Advanced alerting with Grafana Machine Learning
Note: By registering, you agree to be emailed information about this event recording and related product-level information.
Advanced alerting with Grafana Machine Learning
You are registered for this webinar.
You'll receive an email confirmation, and a reminder on the day of the event.
A registration error occurred. Please email update@grafana.com for help.
Event starts in .
You can join now.
Join eventA registration error occurred. Please email update@grafana.com for help.
You can join now.
Join eventA registration error occurred. Please email update@grafana.com for help.
This event has concluded
A recording will be available soon. Sign up to be alerted.
Learn how to augment your static alert thresholds with Grafana Machine Learning. Let us determine when your alerts should fire, predict the future state of your system, or identify misbehaving series within a group. Grafana Machine Learning enables previously impossible scenarios for alerting, with minimal effort.
In this webinar you will learn best practices for using some of our new and advanced features, including:
- Complementing your existing alerts by transcending static thresholds
- How to account for holidays, such as Black Friday, in order to reduce noise when creating adaptive alerts
- How to use outlier detection to alert on misbehaving instances within a group; for example, are your load-balanced Kubernetes pods receiving equal traffic?
- When to choose these advanced features over static thresholds for best results
Additional resources to explore:
Ben Sully
Senior Software Engineer at Grafana Labs
Ben has been working with data for over 10 years. Outside of work he can be found running ultramarathons, where he gets a lot of time to think.
Yasir Ekinci
Senior Software Engineer at Grafana Labs
Yasir has over a decade of experience in machine learning. Besides wrangling the machine, he can be found scuba diving, and tinkering with a homelab.