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
우리는 가장 간단한 역전파(BP), 편파 및 위상 복구, 기계 학습(ML)을 위한 데이터 배열, ML 기반 기호 결정을 합리적으로 결합하여 반복되지 않는 전송 시스템의 최대 거리를 확장하기 위한 복조 프레임워크를 제안합니다. 전처리 단계에서 단일 단계 푸리에 방법을 채택하여 계산 비용을 최소화한 BP를 사용하면 섬유 비선형성 및 색 분산으로 인한 결정적 파형 왜곡이 부분적으로 제거됩니다. 비결정적 파형 왜곡, 즉 편파 및 위상 변동은 정밀한 방식으로 제거될 수 있습니다. 마지막으로, 최적화된 ML 모델은 가장 간단한 BP로는 상쇄할 수 없는 잔류 결정론적 파형 왜곡의 영향을 받아 기호 결정을 수행합니다. 광범위한 수치 시뮬레이션을 통해 DP-16QAM 신호가 광 중계기 없이 표준 단일 모드 광섬유를 통해 240km 이상 전송될 수 있음이 확인되었습니다. 최대 전송 거리가 25km 연장됩니다.
Ryuta SHIRAKI
Kyoto University
Yojiro MORI
Nagoya University
Hiroshi HASEGAWA
Nagoya 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.
부
Ryuta SHIRAKI, Yojiro MORI, Hiroshi HASEGAWA, "Demodulation Framework Based on Machine Learning for Unrepeated Transmission Systems" in IEICE TRANSACTIONS on Communications,
vol. E107-B, no. 1, pp. 39-48, January 2024, doi: 10.1587/transcom.2023PNP0003.
Abstract: We propose a demodulation framework to extend the maximum distance of unrepeated transmission systems, where the simplest back propagation (BP), polarization and phase recovery, data arrangement for machine learning (ML), and symbol decision based on ML are rationally combined. The deterministic waveform distortion caused by fiber nonlinearity and chromatic dispersion is partially eliminated by BP whose calculation cost is minimized by adopting the single-step Fourier method in a pre-processing step. The non-deterministic waveform distortion, i.e., polarization and phase fluctuations, can be eliminated in a precise manner. Finally, the optimized ML model conducts the symbol decision under the influence of residual deterministic waveform distortion that cannot be cancelled by the simplest BP. Extensive numerical simulations confirm that a DP-16QAM signal can be transmitted over 240km of a standard single-mode fiber without optical repeaters. The maximum transmission distance is extended by 25km.
URL: https://global.ieice.org/en_transactions/communications/10.1587/transcom.2023PNP0003/_p
부
@ARTICLE{e107-b_1_39,
author={Ryuta SHIRAKI, Yojiro MORI, Hiroshi HASEGAWA, },
journal={IEICE TRANSACTIONS on Communications},
title={Demodulation Framework Based on Machine Learning for Unrepeated Transmission Systems},
year={2024},
volume={E107-B},
number={1},
pages={39-48},
abstract={We propose a demodulation framework to extend the maximum distance of unrepeated transmission systems, where the simplest back propagation (BP), polarization and phase recovery, data arrangement for machine learning (ML), and symbol decision based on ML are rationally combined. The deterministic waveform distortion caused by fiber nonlinearity and chromatic dispersion is partially eliminated by BP whose calculation cost is minimized by adopting the single-step Fourier method in a pre-processing step. The non-deterministic waveform distortion, i.e., polarization and phase fluctuations, can be eliminated in a precise manner. Finally, the optimized ML model conducts the symbol decision under the influence of residual deterministic waveform distortion that cannot be cancelled by the simplest BP. Extensive numerical simulations confirm that a DP-16QAM signal can be transmitted over 240km of a standard single-mode fiber without optical repeaters. The maximum transmission distance is extended by 25km.},
keywords={},
doi={10.1587/transcom.2023PNP0003},
ISSN={1745-1345},
month={January},}
부
TY - JOUR
TI - Demodulation Framework Based on Machine Learning for Unrepeated Transmission Systems
T2 - IEICE TRANSACTIONS on Communications
SP - 39
EP - 48
AU - Ryuta SHIRAKI
AU - Yojiro MORI
AU - Hiroshi HASEGAWA
PY - 2024
DO - 10.1587/transcom.2023PNP0003
JO - IEICE TRANSACTIONS on Communications
SN - 1745-1345
VL - E107-B
IS - 1
JA - IEICE TRANSACTIONS on Communications
Y1 - January 2024
AB - We propose a demodulation framework to extend the maximum distance of unrepeated transmission systems, where the simplest back propagation (BP), polarization and phase recovery, data arrangement for machine learning (ML), and symbol decision based on ML are rationally combined. The deterministic waveform distortion caused by fiber nonlinearity and chromatic dispersion is partially eliminated by BP whose calculation cost is minimized by adopting the single-step Fourier method in a pre-processing step. The non-deterministic waveform distortion, i.e., polarization and phase fluctuations, can be eliminated in a precise manner. Finally, the optimized ML model conducts the symbol decision under the influence of residual deterministic waveform distortion that cannot be cancelled by the simplest BP. Extensive numerical simulations confirm that a DP-16QAM signal can be transmitted over 240km of a standard single-mode fiber without optical repeaters. The maximum transmission distance is extended by 25km.
ER -