2021-07-02 AI/ML for NFV Meeting Minutes

Sl. No.	Topic	Presenter	Notes
1	Request to create gitlab repo for this incubation project		Sridhar Rao to initiate on 6th of July.
2	Presentation to EUAG		EUAG: End User Advisory Group. 6th of July - Present the plan, and request for support w.r.t Data.
3	Framework Deployment Status	Girish Rohit Singh Rathaur	LF Acumos deployment is not stable - Ended up wasting too much time on it. Move the "framework" issue to later phase - need volunteer(s) to get the issue with these frameworks deployment fixed. Work independent of these framework - Python and ML-Libraries – Jupyter Notebooks. Pod12 - Jumphost. Install Ubuntu 20.04 LTS on Jumphost.
4	Model Deployment Status	Girish Rohit Singh Rathaur	RNN and LSTM – VM failure. Data: https://github.com/amasend/SDN_with_Neural_Network/tree/master/data - CPU
5	Summary of "Gaps" in Existing Failure prediction works	Girish Rohit Singh Rathaur	Container Failures are not considered. Node level failures are not considered. Application level failures are not considered.
6	Model Enhancement Status	Girish Rohit Singh Rathaur	Plan will be based on - 5. Create separate models for each of the failures Girish/Rohit would like to share ideas on Model Enhancement Next week. Node-Level . VM - Current focus. Container/Pod Application/Workload
7	Data Status	Girish Rohit Singh Rathaur	Sridhar Rao to send mail to Ildiko - explaining the requirements.
8.	Failure Prediction Definition - Status	Girish Rohit Singh Rathaur	Classification of Failures Mapping data and failures - ToDo - Node and VM (Rohit), Container and App to Girish. Models and Failure category mapping.