No Breakthrough Yet.

Still Trying with stress-ng (interrupts, system-calls, ...)

Documentation: Pending

Demo

models/failure_prediction/ *.ipynb, models/failure_prediction/static_htmls, models/failure_prediction/data_preprocessing.

Rohit presented his work as part of the 'Final-Presentation' of his Internship.

Beth: Were the results expected? 

Girish/Rohit: 

Steve: Out of 26 features, only 6 features are used. This choice is based on?

Girish/Rohit:

Girish: Going ahead, we will try with better data and improve these models.

Rohit: Continue to contribute to Thoth.

Target date for Whitepaper: October 20th.

Generate Monitoring/logging data using GANs.  This is a new project to create synthetic data for testing of operational ML algorithms.  The idea is to create this data set to be used across the industry as a reference data set.

Hemashree, Vidyashree, Renuka

Openstack Logs: 

Existing Approaches: ELK - Kibana + Alarms.

Analysis: Common approach is using NLP.

Approach:  Google's BERT model for Openstack Logs.

Problems: Anomaly Detection + Pattern Analysis

Deekshita and Rakshita - NLP, Try with Openstack Logs (??)

Data: https://github.com/logpai/loghub/tree/master/OpenStack

Use of NLP for Openstack Logs has already been tried: https://www.cs.utah.edu/~lifeifei/papers/deeplog.pdf .  This work will be used as a reference.