Field Trial of Gaussian Process Learning of Function-Agnostic Channel Performance Under Uncertainty

Fanchao Meng; Shuangyi Yan; Konstantinos Nikolovgenis; Yu Bi; Yanni Ou; Rui Wang; Reza Nejabati; Dimitra Simeonidou

doi:10.1364/OFC.2018.W4F.5

Field Trial of Gaussian Process Learning of Function-Agnostic Channel Performance Under Uncertainty

Fanchao Meng, Shuangyi Yan, Konstantinos Nikolovgenis, Yu Bi, Yanni Ou, Rui Wang, Reza Nejabati, Dimitra Simeonidou

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

1 Citation (Scopus)

372 Downloads (Pure)

Abstract

We model and experimentally demonstrate a novel performance learning method based on monitoring and Gaussian process. After 436km dark fiber transmission the model captures most of the test data with reasonable prediction error and enables a robust QoT predictor.

Original language	English
Title of host publication	2018 Optical Fiber Communications Conference and Exposition (OFC)
Number of pages	3
ISBN (Electronic)	978-1-943580-38-5
DOIs	https://doi.org/10.1364/OFC.2018.W4F.5
Publication status	Published - 2018

Access to Document

10.1364/OFC.2018.W4F.5

Full-text PDF (accepted author manuscript)
This is the author accepted manuscript (AAM). The final published version (version of record) is available online via OSA at https://doi.org/10.1364/OFC.2018.W4F.5 . Please refer to any applicable terms of use of the publisher.
Accepted author manuscript, 727 KB

Handle.net

Persistent link

(INITIATE) The UK Programmable FIxed aNd MobIle InTernet InfrAstrucTurE
Simeonidou, D.
1/02/17 → 31/01/21
Project: Research

Cite this

@inproceedings{a067cf01fd144684a12548e4ef7628a5,

title = "Field Trial of Gaussian Process Learning of Function-Agnostic Channel Performance Under Uncertainty",

abstract = "We model and experimentally demonstrate a novel performance learning method based on monitoring and Gaussian process. After 436km dark fiber transmission the model captures most of the test data with reasonable prediction error and enables a robust QoT predictor.",

author = "Fanchao Meng and Shuangyi Yan and Konstantinos Nikolovgenis and Yu Bi and Yanni Ou and Rui Wang and Reza Nejabati and Dimitra Simeonidou",

year = "2018",

doi = "10.1364/OFC.2018.W4F.5",

language = "English",

isbn = "978-1-5386-5834-5",

booktitle = "2018 Optical Fiber Communications Conference and Exposition (OFC)",

}

TY - GEN

T1 - Field Trial of Gaussian Process Learning of Function-Agnostic Channel Performance Under Uncertainty

AU - Meng, Fanchao

AU - Yan, Shuangyi

AU - Nikolovgenis, Konstantinos

AU - Bi, Yu

AU - Ou, Yanni

AU - Wang, Rui

AU - Nejabati, Reza

AU - Simeonidou, Dimitra

PY - 2018

Y1 - 2018

N2 - We model and experimentally demonstrate a novel performance learning method based on monitoring and Gaussian process. After 436km dark fiber transmission the model captures most of the test data with reasonable prediction error and enables a robust QoT predictor.

AB - We model and experimentally demonstrate a novel performance learning method based on monitoring and Gaussian process. After 436km dark fiber transmission the model captures most of the test data with reasonable prediction error and enables a robust QoT predictor.

U2 - 10.1364/OFC.2018.W4F.5

DO - 10.1364/OFC.2018.W4F.5

M3 - Conference Contribution (Conference Proceeding)

SN - 978-1-5386-5834-5

BT - 2018 Optical Fiber Communications Conference and Exposition (OFC)

ER -

Field Trial of Gaussian Process Learning of Function-Agnostic Channel Performance Under Uncertainty

Abstract

Access to Document

Handle.net

Fingerprint

Projects

(INITIATE) The UK Programmable FIxed aNd MobIle InTernet InfrAstrucTurE

Cite this