Annex G (informative) – Prediction service

This annex is intended to provide some guidelines on how to expose a ChemometricModel prediction service on an existing ADI server.

G.1 Prediction server use case

G.1.2 Main success scenario

Scenario steps	Interface used
1. The client application logs on ADI Prediction server	OPC UA CreateSession
1. The client application reads model from disk and loads them in ADI Prediction server	OPC UA AddNode and write services
1. ADI Prediction server exposes all model structures in its address space	OPC UA address space + ADI data types
1. The client application logs off ADI Predictor server	OPC UA CloseSession
1. The same or another client application logs on ADI Prediction server	OPC UA CreateSession
1. Client application identifies loaded models and their structure	OPC UA Browse address space + ADI data types
1. Client application calls MVAPredict () method with the appropriate input parameters,	OPC UA/ADI method call service + ADI data types
1. ADI Prediction server computes predicted values using vendor native libraries.	Vendor specific native libraries
1. Application reads predicted values from MVAPredict () method output parameters.	OPC UA/ADI method call service + ADI data types
1. Repeat steps 7 to 9 for each model
1. Application logs off from ADI Prediction server	OPC UA CloseSession

Many applications may execute Steps 5 to 11 concurrently.

G.1.2.1 Extensions

1. The client application may pass the input values and received predicted values using OPC UA/ADI address space. However, this approach does not scale up well in multi-user environment because a prediction server is expected to serve many users concurrently which make synchronization almost impossible.
2. In custom / dedicated configurations, the ADI Prediction server loads a predefined set of models, so client applications can use them immediately.