Robust Self-Learning Physical Layer Abstraction Utilizing Optical Performance Monitoring and Markov Chain Monte Carlo

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

doi:10.1109/ECOC.2017.8346217

Robust Self-Learning Physical Layer Abstraction Utilizing Optical Performance Monitoring and Markov Chain Monte Carlo

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

Research output: Contribution to conference › Conference Paper

12 Citations (Scopus)

380 Downloads (Pure)

Abstract

We model and experimentally demonstrate a self-learning abstraction process based on statistical assessment of the real-time monitoring data, both amplifier and non-linear noise parameters are periodically updated which further enables an accurate QoT estimator.

Original language	English
Number of pages	3
DOIs	https://doi.org/10.1109/ECOC.2017.8346217
Publication status	Published - 15 Sept 2017
Event	3rd European Conference and Exhibition on Optical Communication: ECOC 2017 - Gothenburg, Sweden Duration: 17 Sept 2017 → …

Conference

Conference	3rd European Conference and Exhibition on Optical Communication
Country/Territory	Sweden
City	Gothenburg
Period	17/09/17 → …

Access to Document

10.1109/ECOC.2017.8346217

Full-text PDF (accepted author manuscript)
This is the author accepted manuscript (AAM). The final published version (version of record) is available online via IEEE at https://doi.org/10.1109/ECOC.2017.8346217 . Please refer to any applicable terms of use of the publisher.
Accepted author manuscript, 829 KB

Handle.net

Persistent link

Cite this

@conference{75174a7d5b8d44b89d4a3aaa008cf3b3,

title = "Robust Self-Learning Physical Layer Abstraction Utilizing Optical Performance Monitoring and Markov Chain Monte Carlo",

abstract = "We model and experimentally demonstrate a self-learning abstraction process based on statistical assessment of the real-time monitoring data, both amplifier and non-linear noise parameters are periodically updated which further enables an accurate QoT estimator.",

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

year = "2017",

month = sep,

day = "15",

doi = "10.1109/ECOC.2017.8346217",

language = "English",

note = "3rd European Conference and Exhibition on Optical Communication : ECOC 2017 ; Conference date: 17-09-2017",

}

TY - CONF

T1 - Robust Self-Learning Physical Layer Abstraction Utilizing Optical Performance Monitoring and Markov Chain Monte Carlo

AU - Meng, Fanchao

AU - Yan, Shuangyi

AU - Wang, Rui

AU - Ou, Yanni

AU - Bi, Yu

AU - Nejabati, Reza

AU - Simeonidou, Dimitra

PY - 2017/9/15

Y1 - 2017/9/15

N2 - We model and experimentally demonstrate a self-learning abstraction process based on statistical assessment of the real-time monitoring data, both amplifier and non-linear noise parameters are periodically updated which further enables an accurate QoT estimator.

AB - We model and experimentally demonstrate a self-learning abstraction process based on statistical assessment of the real-time monitoring data, both amplifier and non-linear noise parameters are periodically updated which further enables an accurate QoT estimator.

U2 - 10.1109/ECOC.2017.8346217

DO - 10.1109/ECOC.2017.8346217

M3 - Conference Paper

T2 - 3rd European Conference and Exhibition on Optical Communication

Y2 - 17 September 2017

ER -

Robust Self-Learning Physical Layer Abstraction Utilizing Optical Performance Monitoring and Markov Chain Monte Carlo

Abstract

Conference

Access to Document

Handle.net

Fingerprint

Cite this