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
광 전송 네트워크의 용량은 꾸준히 증가해 왔으며 네트워크는 더욱 역동적이고 복잡하며 투명해지고 있습니다. 물리 계층에서 전송 품질(QoT)을 추정하기 위해 최악의 가정을 사용하는 것이 일반적이지만 과도한 프로비저닝으로 인해 마진 요구 사항이 높아집니다. 구축될 라이트 경로에 대한 QoT에 대한 정확한 추정은 프로비저닝 마진을 줄이는 데 중요합니다. 기계 학습(ML)은 네트워크 데이터 분석을 수행하고 자동화된 네트워크 자체 구성을 가능하게 하는 가장 강력한 방법론적 접근 방식 중 하나로 간주됩니다. 본 논문에서는 구축하려는 광 경로의 광신호 대 잡음비(OSNR)를 추정하기 위한 ML의 한 분야인 인공 신경망(ANN) 프레임워크를 제안합니다. 이는 스펙트럼 인접 채널 간의 비선형 간섭과 광학 모니터링 불확실성을 모두 고려합니다. Lightpath의 링크 정보 벡터는 입력으로 사용되며 Lightpath의 OSNR은 ANN 출력의 대상입니다. 추정 정확도에 대한 인접 채널 수의 비선형 간섭 영향이 고려됩니다. 광범위한 시뮬레이션 결과는 제안된 OSNR 추정 방식이 모든 RWA 알고리즘과 함께 작동할 수 있음을 보여줍니다. 충분한 학습 데이터가 제공되면 98% 이상의 높은 추정 정확도와 0.5dB 미만의 추정 오차를 얻을 수 있습니다. ANN 모델 R=보다 정확한 OSNR 추정치를 얻으려면 4개의 인접 채널을 사용해야 합니다. 결과를 바탕으로 새로운 광 경로 프로비저닝을 위해 제안된 ANN 기반 OSNR 추정은 미래 광 전송 네트워크의 마진 감소 및 저비용 운영을 위한 유망한 도구가 될 수 있을 것으로 예상됩니다.
Min ZHANG
University of Electronic Science and Technology of China
Bo XU
University of Electronic Science and Technology of China
Xiaoyun LI
University of International Business and Economics
Dong FU
University of Electronic Science and Technology of China
Jian LIU
Nanjing University of Finance and Economics
Baojian WU
University of Electronic Science and Technology of China
Kun QIU
University of Electronic Science and Technology of China
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
Min ZHANG, Bo XU, Xiaoyun LI, Dong FU, Jian LIU, Baojian WU, Kun QIU, "Artificial Neural Network-Based QoT Estimation for Lightpath Provisioning in Optical Networks" in IEICE TRANSACTIONS on Communications,
vol. E102-B, no. 11, pp. 2104-2112, November 2019, doi: 10.1587/transcom.2018EBP3325.
Abstract: The capacity of optical transport networks has been increasing steadily and the networks are becoming more dynamic, complex, and transparent. Though it is common to use worst case assumptions for estimating the quality of transmission (QoT) in the physical layer, over provisioning results in high margin requirements. Accurate estimation on the QoT for to-be-established lightpaths is crucial for reducing provisioning margins. Machine learning (ML) is regarded as one of the most powerful methodological approaches to perform network data analysis and enable automated network self-configuration. In this paper, an artificial neural network (ANN) framework, a branch of ML, to estimate the optical signal-to-noise ratio (OSNR) of to-be-established lightpaths is proposed. It takes account of both nonlinear interference between spectrum neighboring channels and optical monitoring uncertainties. The link information vector of the lightpath is used as input and the OSNR of the lightpath is the target for output of the ANN. The nonlinear interference impact of the number of neighboring channels on the estimation accuracy is considered. Extensive simulation results show that the proposed OSNR estimation scheme can work with any RWA algorithm. High estimation accuracy of over 98% with estimation errors of less than 0.5dB can be achieved given enough training data. ANN model with R=4 neighboring channels should be used to achieve more accurate OSNR estimates. Based on the results, it is expected that the proposed ANN-based OSNR estimation for new lightpath provisioning can be a promising tool for margin reduction and low-cost operation of future optical transport networks.
URL: https://global.ieice.org/en_transactions/communications/10.1587/transcom.2018EBP3325/_p
부
@ARTICLE{e102-b_11_2104,
author={Min ZHANG, Bo XU, Xiaoyun LI, Dong FU, Jian LIU, Baojian WU, Kun QIU, },
journal={IEICE TRANSACTIONS on Communications},
title={Artificial Neural Network-Based QoT Estimation for Lightpath Provisioning in Optical Networks},
year={2019},
volume={E102-B},
number={11},
pages={2104-2112},
abstract={The capacity of optical transport networks has been increasing steadily and the networks are becoming more dynamic, complex, and transparent. Though it is common to use worst case assumptions for estimating the quality of transmission (QoT) in the physical layer, over provisioning results in high margin requirements. Accurate estimation on the QoT for to-be-established lightpaths is crucial for reducing provisioning margins. Machine learning (ML) is regarded as one of the most powerful methodological approaches to perform network data analysis and enable automated network self-configuration. In this paper, an artificial neural network (ANN) framework, a branch of ML, to estimate the optical signal-to-noise ratio (OSNR) of to-be-established lightpaths is proposed. It takes account of both nonlinear interference between spectrum neighboring channels and optical monitoring uncertainties. The link information vector of the lightpath is used as input and the OSNR of the lightpath is the target for output of the ANN. The nonlinear interference impact of the number of neighboring channels on the estimation accuracy is considered. Extensive simulation results show that the proposed OSNR estimation scheme can work with any RWA algorithm. High estimation accuracy of over 98% with estimation errors of less than 0.5dB can be achieved given enough training data. ANN model with R=4 neighboring channels should be used to achieve more accurate OSNR estimates. Based on the results, it is expected that the proposed ANN-based OSNR estimation for new lightpath provisioning can be a promising tool for margin reduction and low-cost operation of future optical transport networks.},
keywords={},
doi={10.1587/transcom.2018EBP3325},
ISSN={1745-1345},
month={November},}
부
TY - JOUR
TI - Artificial Neural Network-Based QoT Estimation for Lightpath Provisioning in Optical Networks
T2 - IEICE TRANSACTIONS on Communications
SP - 2104
EP - 2112
AU - Min ZHANG
AU - Bo XU
AU - Xiaoyun LI
AU - Dong FU
AU - Jian LIU
AU - Baojian WU
AU - Kun QIU
PY - 2019
DO - 10.1587/transcom.2018EBP3325
JO - IEICE TRANSACTIONS on Communications
SN - 1745-1345
VL - E102-B
IS - 11
JA - IEICE TRANSACTIONS on Communications
Y1 - November 2019
AB - The capacity of optical transport networks has been increasing steadily and the networks are becoming more dynamic, complex, and transparent. Though it is common to use worst case assumptions for estimating the quality of transmission (QoT) in the physical layer, over provisioning results in high margin requirements. Accurate estimation on the QoT for to-be-established lightpaths is crucial for reducing provisioning margins. Machine learning (ML) is regarded as one of the most powerful methodological approaches to perform network data analysis and enable automated network self-configuration. In this paper, an artificial neural network (ANN) framework, a branch of ML, to estimate the optical signal-to-noise ratio (OSNR) of to-be-established lightpaths is proposed. It takes account of both nonlinear interference between spectrum neighboring channels and optical monitoring uncertainties. The link information vector of the lightpath is used as input and the OSNR of the lightpath is the target for output of the ANN. The nonlinear interference impact of the number of neighboring channels on the estimation accuracy is considered. Extensive simulation results show that the proposed OSNR estimation scheme can work with any RWA algorithm. High estimation accuracy of over 98% with estimation errors of less than 0.5dB can be achieved given enough training data. ANN model with R=4 neighboring channels should be used to achieve more accurate OSNR estimates. Based on the results, it is expected that the proposed ANN-based OSNR estimation for new lightpath provisioning can be a promising tool for margin reduction and low-cost operation of future optical transport networks.
ER -