The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Nous avons proposé une plate-forme de diagnostic de réseau autonome pour l'exploitation des futurs réseaux virtualisés et de grande capacité, y compris les services 5G et au-delà de la 5G. En ce qui concerne le seul candidat aux blocs fonctionnels de collecte et d’analyse d’informations dans la plate-forme, nous avons proposé de nouvelles techniques de détection optique utilisant des données de signaux bruts exploitées acquises à partir de récepteurs optiques cohérents numériques. Les données brutes du signal sont capturées avant divers traitements du signal numérique pour la démodulation. Par conséquent, il contient diverses déformations de forme d’onde et/ou bruit lorsqu’il est ressenti à travers les fibres de transmission. Dans cet article, nous avons cherché à détecter deux défaillances possibles dans les lignes de transmission, notamment la courbure des fibres et le décalage du filtre optique, en analysant les données brutes du signal mentionnées ci-dessus à l'aide de l'apprentissage automatique. À cette fin, nous avons implémenté des applications de conteneur Docker dans WhiteBox Cassini pour acquérir des données de signal brutes en temps réel. Nous avons généré un modèle CNN pour les détections en traitement hors ligne et les avons utilisés pour les détections en temps réel. Nous avons confirmé la détection réussie de la courbure de la fibre optique et/ou du déplacement du filtre optique en temps réel avec une grande précision. Nous avons également évalué leur tolérance au bruit ASE et inventé une nouvelle approche pour améliorer la précision de la détection. En plus de cela, nous avons réussi à les détecter même dans la situation d’apparition simultanée de ces pannes.
Yuichiro NISHIKAWA
Tokyo Denki University
Shota NISHIJIMA
Tokyo Denki University
Akira HIRANO
Tokyo Denki University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copier
Yuichiro NISHIKAWA, Shota NISHIJIMA, Akira HIRANO, "Real-Time Detection of Fiber Bending and/or Optical Filter Shift by Machine-Learning of Tapped Raw Digital Coherent Optical Signals" in IEICE TRANSACTIONS on Communications,
vol. E106-B, no. 11, pp. 1065-1073, November 2023, doi: 10.1587/transcom.2022OBP0002.
Abstract: We have proposed autonomous network diagnosis platform for operation of future large capacity and virtualized network, including 5G and beyond 5G services. As for the one candidate of information collection and analyzing function blocks in the platform, we proposed novel optical sensing techniques that utilized tapped raw signal data acquired from digital coherent optical receivers. The raw signal data is captured before various digital signal processing for demodulation. Therefore, it contains various waveform deformation and/or noise as it experiences through transmission fibers. In this paper, we examined to detect two possible failures in transmission lines including fiber bending and optical filter shift by analyzing the above-mentioned raw signal data with the help of machine learning. For the purpose, we have implemented Docker container applications in WhiteBox Cassini to acquire real-time raw signal data. We generated CNN model for the detections in off-line processing and used them for real-time detections. We have confirmed successful detection of optical fiber bend and/or optical filter shift in real-time with high accuracy. Also, we evaluated their tolerance against ASE noise and invented novel approach to improve detection accuracy. In addition to that, we succeeded to detect them even in the situation of simultaneous occurrence of those failures.
URL: https://global.ieice.org/en_transactions/communications/10.1587/transcom.2022OBP0002/_p
Copier
@ARTICLE{e106-b_11_1065,
author={Yuichiro NISHIKAWA, Shota NISHIJIMA, Akira HIRANO, },
journal={IEICE TRANSACTIONS on Communications},
title={Real-Time Detection of Fiber Bending and/or Optical Filter Shift by Machine-Learning of Tapped Raw Digital Coherent Optical Signals},
year={2023},
volume={E106-B},
number={11},
pages={1065-1073},
abstract={We have proposed autonomous network diagnosis platform for operation of future large capacity and virtualized network, including 5G and beyond 5G services. As for the one candidate of information collection and analyzing function blocks in the platform, we proposed novel optical sensing techniques that utilized tapped raw signal data acquired from digital coherent optical receivers. The raw signal data is captured before various digital signal processing for demodulation. Therefore, it contains various waveform deformation and/or noise as it experiences through transmission fibers. In this paper, we examined to detect two possible failures in transmission lines including fiber bending and optical filter shift by analyzing the above-mentioned raw signal data with the help of machine learning. For the purpose, we have implemented Docker container applications in WhiteBox Cassini to acquire real-time raw signal data. We generated CNN model for the detections in off-line processing and used them for real-time detections. We have confirmed successful detection of optical fiber bend and/or optical filter shift in real-time with high accuracy. Also, we evaluated their tolerance against ASE noise and invented novel approach to improve detection accuracy. In addition to that, we succeeded to detect them even in the situation of simultaneous occurrence of those failures.},
keywords={},
doi={10.1587/transcom.2022OBP0002},
ISSN={1745-1345},
month={November},}
Copier
TY - JOUR
TI - Real-Time Detection of Fiber Bending and/or Optical Filter Shift by Machine-Learning of Tapped Raw Digital Coherent Optical Signals
T2 - IEICE TRANSACTIONS on Communications
SP - 1065
EP - 1073
AU - Yuichiro NISHIKAWA
AU - Shota NISHIJIMA
AU - Akira HIRANO
PY - 2023
DO - 10.1587/transcom.2022OBP0002
JO - IEICE TRANSACTIONS on Communications
SN - 1745-1345
VL - E106-B
IS - 11
JA - IEICE TRANSACTIONS on Communications
Y1 - November 2023
AB - We have proposed autonomous network diagnosis platform for operation of future large capacity and virtualized network, including 5G and beyond 5G services. As for the one candidate of information collection and analyzing function blocks in the platform, we proposed novel optical sensing techniques that utilized tapped raw signal data acquired from digital coherent optical receivers. The raw signal data is captured before various digital signal processing for demodulation. Therefore, it contains various waveform deformation and/or noise as it experiences through transmission fibers. In this paper, we examined to detect two possible failures in transmission lines including fiber bending and optical filter shift by analyzing the above-mentioned raw signal data with the help of machine learning. For the purpose, we have implemented Docker container applications in WhiteBox Cassini to acquire real-time raw signal data. We generated CNN model for the detections in off-line processing and used them for real-time detections. We have confirmed successful detection of optical fiber bend and/or optical filter shift in real-time with high accuracy. Also, we evaluated their tolerance against ASE noise and invented novel approach to improve detection accuracy. In addition to that, we succeeded to detect them even in the situation of simultaneous occurrence of those failures.
ER -