Nonlinear auto-regressive neural network model for forecasting Hi-Def H.265 video traffic over Ethernet Passive Optical Networks

Collin Daly, David L. Moore, Rami J. Haddad

Research output: Contribution to book or proceedingConference articlepeer-review

5 Scopus citations

Abstract

Video bandwidth forecasting can help optimize the transmission of video traffic over optical access networks. In this paper, we propose the use of a nonlinear auto-regressive (NAR) neural network model for forecasting H.265 video bandwidth requirements to optimize video transmission within Ethernet Passive Optical Networks (EPONs). The video's constituent I, P, and B frames are forecast separately to improve model forecasting accuracy. The proposed forecasting model is able to forecast H.265 encoded High-Definition videos with an accuracy exceeding 90%. In addition, using the video bandwidth requirement predictions as grant requests within EPONs improved the efficiency of dynamic bandwidth allocation (DBA). The use of nonlinear auto-regressive neural network grant sizing predictions within EPONs reduced the video packet queueing delay significantly when the network was saturated near capacity.

Original languageEnglish
Title of host publicationIEEE SoutheastCon 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538615393
DOIs
StatePublished - May 10 2017
EventIEEE SoutheastCon 2017 - Charlotte, United States
Duration: Mar 30 2017Apr 2 2017

Publication series

NameConference Proceedings - IEEE SOUTHEASTCON
Volume0
ISSN (Print)1091-0050
ISSN (Electronic)1558-058X

Conference

ConferenceIEEE SoutheastCon 2017
Country/TerritoryUnited States
CityCharlotte
Period03/30/1704/2/17

Scopus Subject Areas

  • Computer Networks and Communications
  • Software
  • Electrical and Electronic Engineering
  • Control and Systems Engineering
  • Signal Processing

Keywords

  • EPON
  • H.265
  • NAR
  • Neural network.
  • Nonlinear Auto-regressive
  • Video forecasting
  • Video prediction

Fingerprint

Dive into the research topics of 'Nonlinear auto-regressive neural network model for forecasting Hi-Def H.265 video traffic over Ethernet Passive Optical Networks'. Together they form a unique fingerprint.

Cite this