Primary Goals:

• Integrated installation (still discussing)Integration training host and inference host with SMO/Non-RT RIC/Near-RT RIC

H Feature Scope / Achievements: (still discussing) 

• Kserve adapter

  • Deploy and manage AI models in Near-RT RIC/

  DME Integration with AIML FW
  • Discuss about the R1 interface, DME related demo in

    Non-RT RIC

    project
  • Need to install DME available in g-release and check how it works.

  • Integrate Inference host with O-Cloud( RICDMS ) and Management Func of RIC. 

• Diversify training data source for Training host
  • Obtaining training data from DME in Non-RT RIC 
  • Obtaining training data from influxDB in SMOIntegration plan based on the existing implementation.

• Training pipeline Enhancement

  • Add Provide sample pipelines by default, reducing user effort

  • Simplify the process of adding new training pipeline (reducing the amount of code written by user)

  • Implementation plan

• Integrated installation

  • Integrate with SMO Influx DB 
  • Plan to install as part of SMO first

• • pipeline 

• Integrated installation

  • Provide install script of inference host

  Kserve adapter

  • Implementation plan for deploying models in Near-RT RIC/Non-RT RICRIC 
  • Provide install script of training host in SMONeed to define how to integrate DMS Cli and Management Func. 

Sprint Demo