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 use 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 providers and consumers of the data to collaborate.
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
Introduction
...
Sridhar K. N. Rao
...
Key-Info (info.yaml)
| Code Block | |
|---|---|
|
Intern
Accepted: Rohit Singh Rathaur
| |
---
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
...
Gerrit Details
- Anonymous HTTP: git clone "https://gerrit.opnfv.org/gerrit/thoth"
- Gerrit Repo: https://gerrit.opnfv.org/gerrit/admin/repos/thoth
Contributions
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.
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).
| Sl. No. | Contributor | Contribution | Duration | Certificate of Appreciation OR Contribution | |||
|---|---|---|---|---|---|---|---|
| 1 | Girish L | Survey of:
| 1 Month| View file | | ML-Networking-Telcos (1) (2).xlsx height | 250 | |
Timeline and Goals
...
Phase-1 Goals
- Running ML-Framework with at least 3 existing 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 Weekly Activity
12 weeks, if the Intern is working Full-time.