Versions Compared

Old Version 4

changes.mady.by.user Sridhar Rao

Saved on

compared with

New Version 5

changes.mady.by.user Sridhar Rao

Saved on

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.


Info
titleInfo

PLEASE FOLLOW THESE INSTRUCTIONS

  1. The content of this template is expected to be filled out for the M1 Release Planning Milestone.
  2. Use the "Copy" command, available under the ..., top right of this page, to copy this template into your project wiki. Be sure to set the "Parent page" field correctly for your project wiki.
  3. After you have successfully copied this template into your project wiki, you may delete this info box.

Table of Contents

Overview

Project NameEnter the name of the project
Target Release NameEnter the name of the release you are targeting to deliver (e.g., Jerma)Moselle
Project Lifecycle StateTBD


Scope

This project 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 single problem within a particular category.

Requirements


CategoryJira ReferenceDescription
Model
  1. Existing: Cleanup and publish the existing (FP) one. We may have to publish in a more usable form (part of a framework, or Python program).
  2. Ongoing: Log Analysis (BERT). Openstack Logs (nova-*, neutron-* ...). Currently openstack logs from a very small (3 computes, 2 controller, 1 Storage) openstack setup is being used.
Tools
  1. Existing: Cleanup the AlgoSelector.
  2. Ongoing: Data
Slection
  1. Selection/Anonymization.
  2. Ongoing: Chaos* (stress-ng)  – Used in the testbed (Intel Pod18, for ex.. but restricted to K8S cluster)

Framework

(MaaS)


Upstream: Kubeflow/Acumos.

Thoth: Kubeflow + Supervised Techniques + Integration with important Data-Pipelines/Sources

WhitePaper

(Research effort)


AI/ML & Kubernetes (CN-NFV)

Scope

High level description of the goals for the project

...





Provide a list of features or use cases, documented as Epics or Stories in Jira.  Use the Jira issue insertion feature for Confluence.

...

NameDescription

Format (Container, Compressed File, etc.)

ML-Models
  1. Failure Prediction Model
  2. Log-Analysis
  1. Jupyter notebook
  2. Python Application (Adaptable to ML-Framework)
  3. Containerized ML-Model (Kubernetes based ML-Framework).
Tools

Architecture

High level architecture diagram

...

List any Anuket projects on which this release is dependent and describe the dependency.

External Dependencies

List any external dependencies (OpenStack, ODL, etc.).  Include specific versions, if relevant.RI-1 and RI-2 Deployment

Test and Verification

Describe how the project will be tested and verified.Test Dataset

Risks

List any risks and a plan to mitigate each risk.Availability of dataset

Risk DescriptionMitigation Plan


...