Anuket Project

This survey is to help Anuket-Thoth to Stay 'relevant' to Telco's Needs

Are you familiar with the AI/ML works (solution and systems) present in your organization?

Click for anchor link Familiarity with your Organization's AI/ML works

Choices Your Vote Current Result: (2 Total Votes) Comments
YES.
2 Votes , 100%
NO.
0 Votes , 0%


MOTORS: MOdels - TOols - ResearchStudies

What is more valuable to Telcos?

Click for anchor link We (Thoth) build better (explainable, least-error, accurate) ML-models to important problems

Choices Your Vote Current Result: (1 Total Votes) Comments
5. Very Important
1 Vote , 100%
4. Important
0 Votes , 0%
3. Good to have
0 Votes , 0%
2. Not important
0 Votes , 0%
1. No value addition.
0 Votes , 0%


Click for anchor link We (Thoth) optimize the existing model for important problems

Choices Your Vote Current Result: (1 Total Votes) Comments
5. Very Important
1 Vote , 100%
4. Important
0 Votes , 0%
3. Good to have
0 Votes , 0%
2. Not important
0 Votes , 0%
1. No value addition.
0 Votes , 0%

Click for anchor link We (Thoth) build a flexible* ML-Framework with implementation of important models that can be trained and used.

Choices Your Vote Current Result: (1 Total Votes) Comments
5. Very Important
1 Vote , 100%
4. Important
0 Votes , 0%
3. Good to have
0 Votes , 0%
2. Not important
0 Votes , 0%
1. No value addition.
0 Votes , 0%

Click for anchor link We (Thoth) build tools that can help telcos to build ML-Models

Choices Your Vote Current Result: (1 Total Votes) Comments
5. Very Important
1 Vote , 100%
4. Important
0 Votes , 0%
3. Good to have
0 Votes , 0%
2. Not important
0 Votes , 0%
1. No value addition.
0 Votes , 0%

Click for anchor link We (Thoth) conduct research studies with thorough and systematic analysis of Open-Problems

Choices Your Vote Current Result: (1 Total Votes) Comments
5. Very Important
1 Vote , 100%
4. Important
0 Votes , 0%
3. Good to have
0 Votes , 0%
2. Not important
0 Votes , 0%
1. No value addition.
0 Votes , 0%

Dataset

If we generate dataset in testbeds (Openstack/Kubernetes + Chaos Tools such as litmus + OSS TrafficGens) and use it to train the ML-Models (ex: failure prediction, anomaly detection, etc), how relevant these models will be useful for production networks of Telcos? 

Click for anchor link Relevance of Dataset + Model from Testbed (labs) to the Production

Choices Your Vote Current Result: (1 Total Votes) Comments
Yes. Relevant
0 Votes , 0%
No. It will not be.
0 Votes , 0%
Why do it with testbed dataset when we (Telco) have access to production dataset?
1 Vote , 100%


Frameworks

Telcos have (for past 15-20 yrs - maybe even more) AI/ML systems solving business problems (customer churns) and/or legacy Network management (failures prediction, anomaly detection, etc.).  Is it Important that the ML-models we develop (related to Telco Clouds) should work in these frameworks (of legacy systems) ?

Click for anchor link Integration with legacy AI/ML Systems?

Choices Your Vote Current Result: (1 Total Votes) Comments
YES (we don't want to maintain multiple systems)
1 Vote , 100%
NO (Managed by different silos)
0 Votes , 0%


Models: Importance of AI/ML Problems related to NFV

Please add any other problems you consider that is important here:



Click for anchor link Importance of Failure Prediction (VM)

Choices Your Vote Current Result: (0 Total Votes) Comments
5. Very Important
0 Votes , 0%
4. Important
0 Votes , 0%
3. Good to have
0 Votes , 0%
2. Not important
0 Votes , 0%
1. No value addition.
0 Votes , 0%

Click for anchor link Importance of Failure Prediction (Containers)

Choices Your Vote Current Result: (0 Total Votes) Comments
5. Very Important
0 Votes , 0%
4. Important
0 Votes , 0%
3. Good to have
0 Votes , 0%
2. Not important
0 Votes , 0%
1. No value addition.
0 Votes , 0%

Click for anchor link Importance of Failure Prediction (Links)

Choices Your Vote Current Result: (0 Total Votes) Comments
5. Very Important
0 Votes , 0%
4. Important
0 Votes , 0%
3. Good to have
0 Votes , 0%
2. Not important
0 Votes , 0%
1. No value addition.
0 Votes , 0%

Click for anchor link Importance of Failure Prediction (Apps)

Choices Your Vote Current Result: (0 Total Votes) Comments
5. Very Important
0 Votes , 0%
4. Important
0 Votes , 0%
3. Good to have
0 Votes , 0%
2. Not important
0 Votes , 0%
1. No value addition.
0 Votes , 0%

Click for anchor link Importance of Failure Prediction (Services - control/middleware/)

Choices Your Vote Current Result: (0 Total Votes) Comments
5. Very Important
0 Votes , 0%
4. Important
0 Votes , 0%
3. Good to have
0 Votes , 0%
2. Not important
0 Votes , 0%
1. No value addition.
0 Votes , 0%

Click for anchor link Importance of Traffic Engineering (Ex: Reinforcement Learning)

Choices Your Vote Current Result: (0 Total Votes) Comments
5. Very Important
0 Votes , 0%
4. Important
0 Votes , 0%
3. Good to have
0 Votes , 0%
2. Not important
0 Votes , 0%
1. No value addition.
0 Votes , 0%

Click for anchor link Importance of Other Predictions (resource utilization, attack, SLA-breach)

Choices Your Vote Current Result: (0 Total Votes) Comments
5. Very Important
0 Votes , 0%
4. Important
0 Votes , 0%
3. Good to have
0 Votes , 0%
2. Not important
0 Votes , 0%
1. No value addition.
0 Votes , 0%

Click for anchor link Importance of Resource Optimization (scheduling, deployment scaling, migration, etc.)

Choices Your Vote Current Result: (0 Total Votes) Comments
5. Very Important
0 Votes , 0%
4. Important
0 Votes , 0%
3. Good to have
0 Votes , 0%
2. Not important
0 Votes , 0%
1. No value addition.
0 Votes , 0%

Click for anchor link Importance of Anomaly Detection (metrics, logs, stats)

Choices Your Vote Current Result: (0 Total Votes) Comments
5. Very Important
0 Votes , 0%
4. Important
0 Votes , 0%
3. Good to have
0 Votes , 0%
2. Not important
0 Votes , 0%
1. No value addition.
0 Votes , 0%

Click for anchor link Importance of Alert Filtering/classification - Finding Actionable Alerts

Choices Your Vote Current Result: (0 Total Votes) Comments
5. Very Important
0 Votes , 0%
4. Important
0 Votes , 0%
3. Good to have
0 Votes , 0%
2. Not important
0 Votes , 0%
1. No value addition.
0 Votes , 0%

Click for anchor link Importance of Correlation - as part of causal analysis

Choices Your Vote Current Result: (0 Total Votes) Comments
5. Very Important
0 Votes , 0%
4. Important
0 Votes , 0%
3. Good to have
0 Votes , 0%
2. Not important
0 Votes , 0%
1. No value addition.
0 Votes , 0%

Please add any other comments you would like to share

Comments and Suggestions



  • No labels