Gaussian Process Regression for WDM System Performance Prediction

Jesper Wass, Jakob Thrane, Molly Piels, Rasmus Thomas Jones, Darko Zibar

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

Gaussian process regression is numerically and experimentally investigated to predict the bit error rate of a 24 x 28 CiBd QPSK WDM system. The proposed method produces accurate predictions from multi-dimensional and sparse measurement data.
Original languageEnglish
Title of host publicationOptical Fiber Communication Conference 2017
Number of pages3
PublisherOptical Society of America (OSA)
Publication date2017
Article numberTu3D.7
ISBN (Print)978-1-943580-23-1
DOIs
Publication statusPublished - 2017
EventOptical Fiber Communication Conference 2017 - Los Angeles, United States
Duration: 19 Mar 201723 Mar 2017

Conference

ConferenceOptical Fiber Communication Conference 2017
CountryUnited States
CityLos Angeles
Period19/03/201723/03/2017
Series2017 Optical Fiber Communications Conference and Exhibition (ofc)

Bibliographical note

From the session: Linear and Nonlinear Multicarrier Systems (Tu3D)

Fingerprint Dive into the research topics of 'Gaussian Process Regression for WDM System Performance Prediction'. Together they form a unique fingerprint.

Cite this