Anomaly detection in PFLB Platform#

AI anomaly detection#

Cloud

PFLB Platform enables early detection of non-standard behavior of a system under test online and simplifies the analysis of metrics at the end of the test.

../../_images/um_anomaly.rn9.png

In this version, AI model has learned how to search for 2 types of anomalies:

  • Response Time deviation is extreme response time deviation from average values in a sliding window. On the graph, these are shown in red.

  • VUser and Response Time inverse correlation is the inverse correlation of response time as the number of virtual users changes. For example, response time decreases significantly as the number of virtual users increases. On the graph, these are shown in yellow.

You can view each anomaly in detail in Grafana.

Additional VUser minutes#

Cloud

If you run out of VUser minutes, you no longer have to wait for the next billing cycle to continue your testing.

You can purchase a bundle of 300,000 additional VUser minutes in your account section and continue testing right away:

../../_images/um_service_package_free.rn9.png
../../_images/um_service_package_standard.rn9.png
../../_images/um_service_package_pro.rn9.png

Additional VUser minutes purchased will not expire after a month. It remains available until consumed.

Migrating to Debian for Enterprise version#

Enterprise

With this release, it will be easier for you to deploy the PFLB Platform Enterprise version in your environment. Our platform has migrated from Centos 7, which is no longer being supported by community, to the more popular Debian 12.