https://github.com/chayuto/unsw-thesisb_telescope

Video Traffic Telemetry using SDN
https://github.com/chayuto/unsw-thesisb_telescope

Last synced: 14 days ago
JSON representation

Video Traffic Telemetry using SDN

• Host: GitHub
• URL: https://github.com/chayuto/unsw-thesisb_telescope
• Owner: chayuto
• Created: 2022-03-05T11:12:35.000Z (almost 3 years ago)
• Default Branch: master
• Last Pushed: 2022-04-03T06:40:26.000Z (almost 3 years ago)
• Last Synced: 2024-11-07T10:28:59.054Z (2 months ago)
• Language: Python
• Homepage:
• Size: 18.6 KB
• Stars: 0
• Watchers: 1
• Forks: 1
• Open Issues: 1
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Video Traffic Telemetry using SDN

unsw-thesisb_telescope

## Problem statement

Video traffic is consuming a large portion of bandwidth in carriers’ network. Video traffic is designed to be adaptive traffic to consume bandwidth as much as possible. This is to deliver the best possible video quality from the content providers. Carriers are struggling in coping with the increasing demand and finding ways to monitor and manage such traffic

## Objective

Our objective of this project is to develop a video traffic monitoring tool using Software-Defined Networking (SDN) for ISP, that offers low-cost flow-level monitoring, providing insight of the video flow

## My solution

TeleScope: Flow-level monitoring tool for video traffic with SDN:

‘Bump-in-a-wire’ architecture with minimal disruption to data-plane forwarding

Utilise SDN commodity switch (no specialised hardware) with open-source controller

Dynamically manage rules in SDN switch to minimise processing cost

Utilise Traffic Analyser to inspect packet headers, reducing the control plane overhead

## Contributions (at most one per line, most important first)

Plan and design of the video traffic telemetry tool: TeleScope

Implement fully functional prototype in UNSW SDN Testbed

Validate solution with test scenario 

Assess scalability of the system with hardware traffic generator

Deploy system on live feed traffic and provide useful report for network operator

## Suggestions for future work

Behavioural-based classification of video using flow’s statistical data collected by TeleScope (i.e. using machine learning)