Not a week goes by without us learning about a preventive maintenance case detected by Augtera’s machine learning by a customer.
Today’s short story is this: The customer received a ticket opened by Augtera in their ticketing system (ServiceNow) stating that there is an abnormal rate of environmental alerts found automatically with machine learning.
That’s it: Only one ticket waiting for the operator to click for actionable information.
Once the operator clicks on the link provided in the ticket, the anomaly opens automatically, as in the image below (anomaly in red):
The ML-based anomaly indicates a series of alerts (approximately one per minute) related to the power supply voltage (PEM) being out of range on a specific device. It is important to note that the operator was not notified of these individual alerts, as is the case with traditional tools, but was notified only of the one actionable anomaly.
By clicking on the “View trends” button on the anomaly graph, the operator can directly inspect all similar alerts that have occurred on that device and confirm that the voltage metric available in the alerts is increasing over time.
The following heatmap shows this evolution until the power supply is switched off.
Today, these types of alarms are usually lost in the noise, and operators do not pay attention to them because they do not know how they occur or what their trend is.
Machine learning continuously analyses patterns and automatically detects abnormal changes in all alarms. This reveals preventive use cases that were not possible before.
The real question for you and your organization is: do you want to be the person who takes action in the event of an emergency power outage at 2am, or do you want to be the person who shuts off that power during a preventive maintenance operation during the weekly site visit?
To schedule a 30-minute discussion with an engineer on how Augtera Network AI can help with your network challenges please contact us. Thanks for reading our blog.
