Working with queuing network models

Use a queuing network model (QNM) to estimate service performance against changes in business driver volumes or infrastructure configuration. It can predict saturation, system utilization, throughput, queue length, and response time based on the impact of business drivers running on systems.

These metrics are either computed for a single resource or for a complex network. Predicted values are then automatically compared with the service levels specified as thresholds on response time and utilization.

To predict saturation based on business drivers growth, a Performance vs. Load analysis must exist for the current domain. The model creation wizard prompts you to select the PLA analysis, and displays the available resource types based on the selected analysis. 

Related topics

Modeling-capacity-usage

Working-with-time-forecasting-models

Working-with-extrapolation-models

The following table specifies the system resource types supported by QN models, including the corresponding metrics:


After you create a QNM model, you can add a scenario and perform a what-if analysis to simulate scenarios, such as hardware and system changes, and find the appropriate configuration that suits your requirements. You can also apply a calibration to a model to improve the response time estimates across all scenarios of the model. 

QNM_overview.png

For more information about how to work with QNM, see the following topics:

 

Tip: For faster searching, add an asterisk to the end of your partial query. Example: cert*