AI/ML for NFV Usecases
6 is the number of Thoth, and Ibis/Beak-of-Ibis is one of the symbols of Thoth - The above symbol captures both.
Introduction
AI has the potential in creating value in terms of enhanced workload availability and improved performance and efficiency for NFV usecasesuse cases. This work aims to build machine-Learning models and Tools that can be used by Telcos (typically by the operations team in Telcos). Each of these models aims to solve a single problem within a particular category. For example, the first category we have chosen is Failure prediction, and we aim to create 6 models - failure prediction of VMs. Containers, Nodes, Network-Links, Applications, and middleware services. This project also aims to define a set of data models for each of the decision-making problems, that will help both provider providers and consumer consumers of the data to collaborate.
Name
Presentations
12-November-2021 Updated: 19-November |
| ||||||
| 10-July-2021 |
|
...
Approach
Decision-Driven Data Analytics.
https://mitsloan.mit.edu/ideas-made-to-matter/decisions-not-data-should-drive-analytics-programs
PTL
Committers
Sridhar K. N. Rao (Sridhar Rao)
Intern
Key-Info (info.yaml)
...
| Code Block |
|---|
...
|
In discussion: 4 CS/Math Students.
| |
---
project: 'Thoth'
project_creation_date: '01 June 2021'
project_category: 'Infrastructure' # One of: Deployment, Integration & Testing, Infrastructure
lifecycle_state: 'Incubation' # One of: Incubation, Mature, Integration, Archived
project_lead: &anuket_PROJECTNAME_ptl
name: 'Rohit Singh Rathaur'
email: 'rohitrathore.imh55@gmail.com'
company: 'Birla Institute of Technology, Mesra'
id: 'TeAmp0is0N' # Linux Foundation ID
timezone: 'IST ((GMT+5:30)'
primary_contact: *anuket_PROJECTNAME_ptl
issue_tracking:
type: 'jira'
url: 'https://jira.anuket.io/projects/thoth'
key: 'thoth'
mailing_list:
type: 'groups.io'
url: 'anuket-tech-discuss@lists.anuket.io'
tag: 'thoth'
realtime_discussion: # Fields may be blank if no realtime discussions
type: 'slack'
server: 'anuketworkspace.slack.com'
channel: '#thoth'
meetings: # Fields may be blank if no standing meetings
- type: 'zoom'
agenda: 'https://wiki.anuket.io/display/HOME/Thoth-Meeting+Minutes' # eg: 'https://wiki.anuket.io/display/HOME'
url: 'https://zoom.us/j/96163911066' # eg: 'https://global.gotomeeting.com/join/819733085'
repeats: 'bi-weekly' # ex: weekly, monthly, bi-weekly
time: '13:00 UTC' # ex: '16:00 UTC'
repositories:
- 'thoth' # ex: myproject
committers:
- name: 'Sridhar K. N. Rao' # repeat all fields for each committer
email: 'srao@linuxfoundation.org'
company: 'The Linux Foundation'
id: 'sridharkn'
tsc:
# yamllint disable rule:line-length
approval: 'https://wiki.anuket.io/display/HOME/2021-08-03+TSC+Agenda+and+Minutes' # ex: https://wiki.anuket.io/display/HOME/2021-01-12+TSC+Agenda+and+Minutes
changes:
- type: ''
link: ''
# yamllint enable rule:line-length
|
Contributors
Meeting Details
Topic: AI/ML for NFV
Time: 13:00 Universal Time UTC
...
Meeting ID: 961 6391 1066
Find your local number: https://zoom.us/u/acEvZCMvjT
Weekly Meeting minutes
Gerrit Details
- Anonymous HTTP: git clone "https://gerrit.opnfv.org/gerrit/thoth"
- Gerrit Repo: https://gerrit.opnfv.org/gerrit/admin/repos/thoth
...
Contributions
| Sl. No. | Contributor | Contribution | Duration | Certificate of Appreciation OR Contribution |
|---|---|---|---|---|
| 1 | Girish L | Survey of:
| 1 Month |
Timeline and Goals
...
Phase-1 Goals
- Running ML-Framework with at least 3 existing (enhanced) models for NFV.
- Generate Synthetic Data using ML.
- Identify 3 problems for which ML can be applied in NFV - For which no acceptable models exist.
- Identify the ML technique that can be used for these problems.
Phase-1 Bonus
- Build Two Tools
- AlgoSelector
- TVLVapp
Phase-1 Weekly Activity
12 weeks, if the Intern is working Full-time.
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.
Share the State of the art survey.
Provide initial gap analysis.
Understand the art of publications and OS projects. Decided to go with LFN Acumos. Chose a problem domain: Failure Prediction to start working with. Completed the reading papers related to Failure Prediction and updated the implementation details till now whatever I have got.
Status: Completed
1-page report where mentioned failures and what type of failures.
Deploy the ML Framework (Tentative: LFN Acumos).
- Document the usage workflow
- Try any existing model.
Provide access to the server(s).
Intel Pod?
|
Collect, analyze and document the implementation of 3 existing models for NFV.
Collect the data.
Deploy the models on the framework (2)
Collect the data (contd).