Compute resource options for Decision Optimization
When you run a Decision Optimization model, you use the Watson Machine Learning instance that is linked to the deployment space associated with your experiment.
Default hardware configuration
The following hardware configuration is used by default when running models in an experiment:
| Capacity type | Capacity units per hour (CUH) |
|---|---|
| 2 vCPU and 8 GB RAM | 6 |
The CUH is consumed only when the model is running and not when you are adding data or editing your model.
You can also switch to any other experiment environment as required. See the Decision Optimization plans for a list of environments for Decision Optimization experiments.
For more information on how to configure Decision Optimization experiment environments, see Configuring environments.
Compute usage in projects
Decision Optimization experiments consume compute resources as CUH from the Watson Machine Learning service.
You can monitor the total monthly amount of CUH consumption for the Watson Machine Learning service on the Resource usage page on the Manage tab of your project.
What consumes CUH?
Capacity unit hours (CUH) are consumed for running assets, not for working in tools. That is, there is no consumption charge for defining Decision Optimization experiments, but there is a charge for running the experiment. Similarly, there is no charge for defining a deployment or deployment job for a decision optimization solution, but there is a charge for running a deployment job or inferencing against the deployed solution.
Learn more
- Decision Optimization
- Watson Machine Learning plans and compute usage
- Monitoring account resource usage
Parent topic: Choosing compute resources for tools