Skip to Content

SAP PA 3.1 capabilities to push processing to HANA ?

Will you be able to provide more insights into using HANA capabilities for training and validating models ? If I connect to HANA database as a source in my desktop SAP PA modeling tool( I have enabled delegation as well) will the training and validation of data happen in HANA or on SAP PA server /local machine ?

Add comment
10|10000 characters needed characters exceeded

  • Get RSS Feed

3 Answers

  • Best Answer
    Dec 05, 2016 at 07:47 AM

    Hi Sainath, the creation of predictive models is delegated in the case of SAP HANA. It means the data will not exit the HANA box (no transfer to the PA client) and APL will do all the heavy processing inside SAP HANA. See https://uacp2.hana.ondemand.com/viewer/c36bc49d7cce4d35a2099aecdea81e2c/3.1/en-US/0d945c7f65a945588c3267eee669ae16.html for the APL delegation prerequisites. There is a still a need to deploy a PA server, in case SAP HANA is the underlying data source, this is really just used to be able to produce the debriefing graphs.

    Hope this helps & clarifies. Please accept the answer if this does.

    Thanks & regards

    Antoine Chabert

    Add comment
    10|10000 characters needed characters exceeded

  • Dec 06, 2016 at 07:19 AM

    Great then! you are welcome!

    Add comment
    10|10000 characters needed characters exceeded

  • Dec 06, 2016 at 07:21 AM

    And to be noted: we do have similar capabilities in the Spark/Hadoop world, this is nicknamed "Native Spark Modeling".

    Add comment
    10|10000 characters needed characters exceeded