AI/ML Models for NFV Usecases
- Sridhar Rao
- Jim Baker
- Girish
Internship Projects/Mentors
Title | AI/ML Models for NFV Usecases |
Status | Approved |
Difficulty | High |
Description
This project aims to deploy and run AI/ML models for NFV-usecases. Any two of the following three problems can be considered. .
VNF/CNF Placement
VNF/CNF resource/performance/failure prediction
Packet-Loss Classification
Problem | Model | Link | Comments |
|---|---|---|---|
Prediction of VNF Resource Demands | RNN, LSTM | ||
VNF Placement | Neural Network Model (MLP) |
Additional Information
LFN Acumos: https://www.acumos.org/
TensorFlow Time Series : https://www.tensorflow.org/tutorials/structured_data/time_series
Collectd : https://collectd.org/
Hosting Repo: As a Subproject under CIRV - https://github.com/opnfv/cirv
Learning Objectives
ML Techniques: Deep_learning.
ML model development
AI/ML for Telco Usecases.
Expected Outcome
Enhance Acumos with model for NFV/Telco Usecases.
Run Acumos with these enhancements in Anuket Testbeds.
Comprehensive report on applications of AI/ML in Networking(Comparative analysis).
Relation to LF Networking
Will be part of Anuket.
Education Level
Undergraduate
Skills
Knowledge of ML and ML-Tools - Tensorflow.
Future plans
This work is the first step toward use of AI/ML in Telecom Networks, it can be enhanced to more useful and complex usecases.
Preferred Hours and Length of Internship
Part-Time
Mentor(s) Names and Contact Info
Sridhar K. N. Rao
Spirent Communications
Volunteers
Girish L. (PhD Student)
VTU