Fiduciaria moves from a reactive to a proactive model of hardware monitoring through machine learning.
Summary:
A company in the financial sector did not have proactive visibility of their infrastructure, their ability to react was limited, because they had to wait for an alert when the capacity of their hardware was at its limit. Panorama Technologies supported the implementation of a solution that would allow the administrator and infrastructure managers to:
- Have total visibility of the performance and availability of their technological components: machines, Swiths.
- Apply a future forecast or preventive model to machine disks.
- Proactively alert to prevent disk space shortages in advance.
Challenges
Implement the functionalities of the Machine Learning application, which uses artificial intelligence concepts.
Achieving the following visibility for each machine of the following:
-
- Total disk capacity
- Prediction of behavior at X time
- Behavior and average elapsed time
It was initially achieved with the information for each disk of the behavior of x time ago. Important data for the artificial intelligence to be able to apply the Forecast of the data.
The “Predict Numeric Fields” functionality was used, since it allows to perform prediction experiments starting from a
Once the experiment was finished, the application helped us to generate the code:
Use cases
Implement Capacity Planning (Machine Learning) to disk components of all your devices and/or platforms where applicable.
Impacted areas
IT Infrastructure and Operations.
Integrated Data Sources
- Windows (System Logs).
- Linux (System Logs).
- Appliance (Availability Scripts).
- Availability services (server scripts).
- Capacity Planning (Machine Learning).
Solution
Splunk Enterprise
Results
Thanks to the implementation of Splunk Machine Learning, it was possible to consolidate all the information in a single point, allowing the future visualization of the disk behavior of all its components. In this way, infrastructure administrators can address possible incidents caused by disk space in advance.
