Date

Feb 17, 2021

Attendees

LF Staff:  @Jim Baker @Kenny Paul (Deactivated), @Trishan de Lanerolle , @Brandon Wick
Committee Members: @Massimo Massimo @Fernando Oliveira, @Kodi
TAC: @Ranny Haiby, @Martin Jackson, @Georg Kunz, @Christian Olrog, @Frank Brockners , @Al Morton , @FREEMAN, BRIAN D , @Jason Hunt, @Olaf Renner (Nokia)

Guests: @Eman Gil @Anil Kapur, @Tina Tsou (Deactivated) , @Vishnu Ram OV 

Agenda

• Start the Recording

• Antitrust Policy

• Agenda Bashing (Roll Call, Action Items (5 minutes)

• General Topics

  • Review the vDTF notes and set priorities

  • Co-meet with TAC and discuss AI/ML data sharing project

Minutes

Questions:

• What else would you expect regarding AI with ONAP? maybe start from our Control Loop mechanisms and then add AI/ML? 

• Is there any network automation/autonomy use-case specific model that could be enabled by Acumos Market?

• What would an OVP3.0 test suite test? 

  • How can we validate that the algorithms actually work in production? 

• What is the TM Forum Spec for network intelligence ? IG1230 TMF ANP

  • What is the common platform and where should it be hosted?

  • What types of labs do we actually need? 

• How can Operators share data with open source communities to create algorithms or even models?   

  • Anonymous data sharing issue has been solved for the medical industry stripping out HIPPA data, etc. That is a much bigger problem than sharing networking data.

• What are the expectations Operators that create their own AI algorithms and models themselves have from open source communities, is it just the generic Data Analytics Framework platform?

• What AI/ML testing already exists with the Operators

  • @Ranny Haiby ia aware of some work that has been done:

    • Congestion prediction and mitigation - This use case will demonstrate how AI/ML may be used to predict congestion and perform closed loop automation for executing configuration changes to mitigate.

    • Sleeper Cell Detection - Predict a cell going to "sleep" and handover a critical UE (e.g. ambulance) to another cell.

    • Traffic Steering - Improve Quality of Experience (QoE) by steering UE traffic among multiple cells.

• @Massimo Massimo shared info on TIM Big Data challenges - (data lake no longer exists) https://www.slideshare.net/rajeshwerkushwaha/telecom-italia-big-data-challenge 

  • Also pointed out this project:  https://www.opalproject.org/about-opal

  • TMF has AI & DAta Analytiucs project. An initiative is is producing an AI Model Data Sheet, Anaother iniziative is on Data Governance with a Data Governance White Paper ( IG 1225)

• @Vishnu - ITU-T ran a AI/ML in 5G Challenge in 2020: https://www.itu.int/en/ITU-T/AI/challenge/2020/Pages/default.aspx There are a bunch of problem statements (use cases) and data, from operators.

• @FREEMAN, BRIAN D some work and royalties may be required to make this work

• Possible approaches

  • is to select a single usecase and use that to understand the challenges around sanitizing the data

  • create a lab that can be used by the operators to test algorithms  

  • sharing models and algorithms only

  • share "insights", much like security threat analytics might be shared.  Depends on use case.  Perhaps network resiliency or fraud use cases would apply to insight sharing?

  • Can any usecases be inferred from the survey at all?    Question #8  most operators already have AI efforts in play for all of these items. 

POSSIBLE USECASES:

• Sleeper cell detection

• Congestion prediction and mitigation

• Traffic Steering

Action items