Anuket Project

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

Compare with Current View Page History

« Previous Version 18 Next »

Introduction


Advisors

  1. Sridhar K. N. Rao (Sridhar Rao)

Intern

Accepted: Rohit Singh Rathaur


Meeting Details

Topic: AI/ML for NFV
Time: 13:00 Universal Time UTC

Day: Every week on Friday
Zoom Link: https://zoom.us/j/96163911066

Meeting ID: 961 6391 1066
Find your local number: https://zoom.us/u/acEvZCMvjT


Weekly Meeting minutes

04-June-2021


Volunteer Contributions


Sl. No.ContributorContributionDurationCertificate of Appreciation OR Contribution
1Girish L

Survey of:

  1. Existing works on AI/ML in Networking - works related to NFV - problems, ML-Techniques, Data, etc.
  2. NFV Problems - Event Correlation, VNF Placement, Anomaly Detection, VNF Failure Prediction, and Synthetic Data Generation.
  3. OSS Projects for AI/ML that can be (re)used
1 Month










Timeline and Goals

PhaseTime
130 November 2021


Phase-1 Goals 

  1. Running ML-Framework with at least 3 existing models for NFV.
  2. Generate Synthetic Data using ML.
  3. Identify 3 problems for which ML can be applied in NFV - For which no acceptable models exist.
  4. Identify the ML technique that can be used for these problems.

Phase-1 Weekly Activity

12 weeks, if the Intern is working Full-time.


Sl. No.Activity by Intern/Researcher(s)                                                              WeekComment / Support from Advisor (s)               
1

Understand the state of art - Publications and OS projects

Analyze the Gaps.

Create a 1-Page report based on the analysis.

Identify the problems in NFV for which the techniques are still not good enough.

1.5

Share the State of the art survey.

Provide initial gap analysis.

2

Deploy the ML Framework (Tentative: LFN Acumos).

  • Document the usage workflow
  • Try any existing model.
1.5

Provide access to the server(s).

Intel Pod?

3

Collect, analyze and document the implementation of 3 existing models for NFV.

Collect the data.

1Provide the 3 models to use.
4

Deploy the models on the framework (2)

Collect the data (contd).

1None.
5Test and optimize the models - If possible.2Suggestions for optimization approaches.
6Study ML technique for Synthetic time-series data generation (STSDG)1Suggest the right technique
7Implement the technique for STSDG2
8Test and optimize STSDG1
9Knowledge Transfer, Handoff (Buffer)1
  • No labels