Anuket Project

Skip to end of metadata
Go to start of metadata

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

Compare with Current View Page History

« Previous Version 4 Current »

Attendees

Sridhar Rao

Girish

Al Morton

Beth Cohen

Ildiko

Kanak Raj

Michael Salmon

Sandra Jackson (Deactivated)

Jahanvi Ojha

Akanksha Singh


Sl. No.TopicPresenterNotes
1Project Creation Status
  1. Jira is still pending.
  2. Committer rights is pending too. It should be resolved today.

Once committer rights is obtained, will publish the 'research-studies'

2Data Generation Status

K8S: Cloudstress for emulating failures.

Currently unable to create failures. Alternate approaches:

  1. More pods with stress-tool - 20-30pods could help. Use a pattern of deploying - step, random-time-varied.
    1. Increase the iops to 10x more than the specified (by the vendor).
  2. Run different application - Openstack is one example
3Data collection through collaboration
No Progress Yet.
4Model (FP) development Status

Simpler:

  1. Completed: Decision Tree
  2. Completed: XG-Boost

Novel/Complex:

  1. Completed - LSTM 
  2. In Progress - GNN

Demo on 3rd September.

All are on Jupyter Notebook, and currently running Google Collaborator.

5Tools - Algoselector Update

https://github.com/opensource-tnbt/algoselector 

Kanak, Jahnavi and Akanksha - 

(ML is applicable or Not)

Supervised

Unsupervised

Reinforced

Sridhar Rao to schedule a meeting with Students to explain the code.

6Other Tools
  1. Model based, Multi-Source Data Extraction with Data Anonymizer

Data Anonymizer:

Exclusions:

  1. Columns.
  2. Rows with certain 'regex'

Prometheus + Elastic

No Progress - Looking for contributors here.

5Other Open-Works

Analysis: Trend and Pattern

Detection: Anomaly Detection

No progress - Looking for contributors here.

  • No labels