Prediction and Optimisation Runtime
The Prediction and Optimisation Run-time component in the i4 platform integrates data processing algorithms, provides an API for accessing embedded algorithms, supports multiple instances, and utilizes Docker containers. Users can search for algorithms, adapt or create new ones, embed them in the run-time, and configure and utilize them throughout the AI Analytics Run-time component. The component includes a Gunicorn Server, Redis and MongoDB databases, and allows algorithms to be developed independently and injected using a Docker parent image.
Benefits
The main advantages of deploying a data processing algorithm as a PO Run-time:
- Seamless integration into the ZDMP platform. The main benefits are:
- Efficient development to deployment in ZDMP platform
- Easily access data published on the ZDMP platform
- Share data processing results with components/zApps on the ZDMP platform
- Standardised API which allows existing components/zApps to use the newly published algorithms
- Application Run time providing Minizdmp platform that allows to deploy PO Run-time component locally.
Data source selection
Output source selection
Continuous or one-time calculation
Modification of algorithm parameters
Additional resources
Learn more about i4FS by visting the project website for general information, the wiki for information about the core components, the Technical Manual for API documentation, and downloading the repository’s source code.
Training Academy
Get a better understanding of the global architecture and information flow.
Software Documentation
Read our easy to follow documentation to learn how to use the i4 Components.