NOTE: This xApp is obsolete - for ML-based xApps, take a look at AD and QP xApps.

This page documents ideas and techniques related to using ML techniques in the RIC/xApps (under O-RAN).

Documentation related to the Amber release of this xApp can be found here.

There are many ways ML could be used in the RIC and how the ML techniques could be embedded in the xApps. Therefore, the following are just examples

Using Acumos ML models in the RIC - demo link

Goal is to support ML models in non-real time and near-real time RIC usecases.
- quickly import an Acumos model into RIC and adapt it into as an xApp (near-real time).
- deploy Acumos models as is into non-real time (mostly on ONAP side).
Priority is to get something working with minimal changes possible on ML models
- focus on performance in the later releases, since many ML models take some time to execute anyway.
Build a standard xApp/Acumos microservice adapter
- deployed along with the Acumos ML model in one Kubernetes pod.
Adapter speaks RMR protocol to RIC
- communicates with the Acumos ML model in the standard http / GRPC manner.
Configuration needed for each deployment
- to tell adapter how to speak with Acumos ML model.
- can be auto generated using ML model protobuf definition.
Consider writing custom RMR model runner
- for performance in near-real time RIC xApps in the following releases.

Slide deck with Acumos intro and ML based xApp design for Amber release

Gerrit Repo

https://gerrit.o-ran-sc.org/r/admin/repos/ric-app/ml

Why Acumos?

In short, the unique features are 1) Distributed AI Marketplace, 2) Interoperable ML Microservices, and 3) Common Open Source Framework to AI.

To expand more on advantages:

Standardized platform and easy export and Docker-file deployment to any environment, including major public clouds, make stand-up and maintenance a breeze.
Simplified toolkit and model onboarding helps data scientists focus on building great AI rather than maintaining infrastructure.
Visual design editor and drag-and-drop application design and chaining lets trainers and other end users deploy normally complicated AI apps for training and testing in minutes.

https://www.acumos.org/

How-to onboard ML model into Acumos - demo video for AI/ML experts

soup-to-nuts wiki page

Is there any company currently using Acumos?

Yes, Ericcson, Huawei, Orange, AI4EU, AT&T, and TechM successfully deployed and using Acumos instances. For reference LF public instance - http://marketplace.acumos.org;