Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

...

Near-Real-time RIC X-APPs (RICAPP)

Primary Goals: Expand the community working on open source xApps for O-RAN SC. Enhance the set of open source xApps in support of the R-SAC use cases (traffic steering, network slicing) as well new use cases. Update and enhance existing xApps to take advantage of the new features in xApp SDK (implemented by the xApp frameworks in C++, go, and python).

E release plan (12-01-21):

  • New xApps: RC (RAN Control) by Mavenir - implements subset of E2 SM RC
  • Improved xApps:
    • LP (Load Prediction) by ChinaMobile: Include trained ML model, will populate predictions in inFlux DB
    • AD (Anomaly Detection) by HCL: Will identify a new anomaly type (area anomaly), use geo-location as a feature. Dependency on Data Stream from KPIMON to influxDB. (Currently AD is working on Static data).
    • QP (QoE Predictor) by HCL: Include prediction for current serving cell, incorporate predicted load as a feature, provide sequence of predictions.
    • TS (Traffic Steering) by UTFPR (University, Parana, Brazil): Call RC xApp to trigger UE handover, improvements in traffic steering logic.
    • Bouncer by HCL: Increase performance and functional testing capabilities; continue identifying RIC platform bottlenecks.
    • HW (HelloWorld) demo xApps in C++, go and python by AT&T and Samsung: Add usage of more platform features, update usage of platform features that are evolving.
  • Integration of AD, QP, TS, LP, RC, and KPIMON with Viavi simulator.
  • Extensive performance benchmarking of the RIC platform using Bouncer and E2 Simulator (HCL)
  • Design for xApps to support network slicing use case.

PTL: SUNIL SINGH  (former PTL still helping out: Matti Hiltunen)

Jira: Count of Epics, User Stories, Tasks, and Issues:  165 issues

E release highlights/accomplishments (12-14-21):

  • The release introduces a new xApp RC (RAN Control) from Mavenir. RC implements a subset of the new E2 SM RC to support traffic steering end to end use case.
  •  QP (QoE Prediction) xApps from HCL include prediction for current serving cell, incorporate predicted load as a feature, provide sequence of predictions.
  • The Bouncer xApp from HCL ....test RIC platform with Multiple E2Sim nodes. 
  • The LP (Load Prediction) xApp from CMCC now includes a trained ML model (and the issue of how to handle large trained ML models was resolved.)
  • The TS (Traffic Steering) xApp maintained by the Federal Technological University of Parana, Brazil includes the ability to call the new RC xApp via gRPC-based interface.
  • The demo HW (HelloWordHelloWorld) xApps in python and go from Samsung include additional functionality.
  • The AD, QP, and TS xApps have been integration tested using Viavi E2 tester.

E release source code, container images and deployment instructions

Each repository has a branch named "e-release" that can be accessed using git. For example, the source code for the AD xApp can be retrieved using  "git clone --branch e-release "https://gerrit.o-ran-sc.org/r/ric-app/ad". The other xApps in the E release can be found at ric-app/qp, ric-app/ts, ric-app/lp, ric-app/hw, ric-app/hw-go, ric-app/hw-python, ric-app/mc, ric-app/bouncer, ric-app/rc, and scp/ric-app/kpimon. Note that the other ric-app repos are obsolete.

Note that this branch is in maintenance and all new development is done in branch "master".

In order to deploy the E release xApps,  you can re-use the pre-created container images as defined here and the instructions on testing the xApps can be found here.


...