Path Asymmetry Reconstruction via Deep Learning

Nada Alhashmi, Nawaf Almoosa, Gabriele Gianini

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Scopus citations

Abstract

This paper proposes a novel scheme to enhance the accuracy of packet-switched network synchronization systems by estimating path asymmetry (PA) using convolutional denoising autoencoders (CDAEs). Network synchronization is a key enabler of several emerging applications, with increasingly tight accuracy requirements especially for 5G. Path asymmetry, which arises due to physical and stochastic network conditions, severely degrades synchronization accuracy. In this paper, we propose a novel technique based on the IEEE Precision Time Protocol (PTP), which accurately reconstructs PA information from PTP packets. The proposed PA estimator can be integrated with existing synchronization systems as a pre-processing method to enhance the overall performance. Simulation results using industry-standard traffic profiles demonstrate significant improvements in PA estimation accuracy compared to the state of the art.

Original languageBritish English
Title of host publicationMELECON 2022 - IEEE Mediterranean Electrotechnical Conference, Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1171-1176
Number of pages6
ISBN (Electronic)9781665442800
DOIs
StatePublished - 2022
Event21st IEEE Mediterranean Electrotechnical Conference, MELECON 2022 - Palermo, Italy
Duration: 14 Jun 202216 Jun 2022

Publication series

NameMELECON 2022 - IEEE Mediterranean Electrotechnical Conference, Proceedings

Conference

Conference21st IEEE Mediterranean Electrotechnical Conference, MELECON 2022
Country/TerritoryItaly
CityPalermo
Period14/06/2216/06/22

Keywords

  • Deep Learning
  • IEEE 1588 Precision Time Protocol
  • Machine Learning
  • Path Asymmetry
  • PTP
  • Time Synchronization

Fingerprint

Dive into the research topics of 'Path Asymmetry Reconstruction via Deep Learning'. Together they form a unique fingerprint.

Cite this