You are viewing an old version of this page. View the current version.

Compare with Current View Page History

« Previous Version 9 Next »

<<Work in progress>> - draft design to facilitate the  Acumos integration with DCAE


For Frankfurt release, DCAE will add new software component "Acumos-DCAE Adapter" which will provide a client interface to receive ML models from an Acumos catalog to ONAP DCAE.  This adapter will generate the required metadata artifacts (Microservice component spec, data-format) and to onboard them directly into the DCAE CLI-DB.  The subsequent Service Assurance flow design, Microservice configurations, and blueprint generation will be supported by the new DCAE MOD components, which will be delivered under Frankfurt Self Serve Control Loops v2

The "Acumos-DCAE Adapter" transforms an Acumos ML model into an ONAP compatible DCAE Microservice in order for it to run in an ONAP DCAE environment.

  1. The Adapter provides a DCAE model runner to wrap the ML model from Acumos to in order to produce a mircorservice that is compatible in DMaaP environment.
  2. The Adapter generates Microservice metadata (i.e., the Component Spec.json and Dataformat.json) for onboarding to DCAE Design environment.
  3. The Adapter generates k8s/Docker executable image for onboarding to DockerCentral (Nexus).

Architecture


Adapter API

  1. The "Acumos-DCAE Adapter" supports Acumos E5 client interface for federated ML models from an Acumos catalog. 
  2. The "Acumos-DCAE Adapter" uses DACE Onboarding APIs for automated mS onboarding to CLI-DB, also submits the mS Image to DockerCentral image repository.

Sample Models

https://gerrit.acumos.org/r/gitweb?p=python-dcae-model-runner.git;a=tree;f=example;h=9ed808e722fbf266eac9e7e9ff583a5848e78a5b;hb=f9574de3a8ea3ec3e34c09a28e141f797eb59d6e


Repository

TBD

Usecase Targeted for Frankfurt


Deliverables


Validation


Post Frankfurt Plans







  • No labels