Sample-distribution-matching-based transfer learning for QoT estimation in optical networks

被引:5
作者
Gu, Zhiqun [1 ]
Qin, Tangze [1 ]
Zhou, Yuhang [1 ]
Zhang, Jiawei [1 ]
Ji, Yuefeng [1 ]
机构
[1] Beijing Univ Posts & Telecommun, State Key Lab Informat Photon & Opt Commun, Beijing 100876, Peoples R China
基金
中国国家自然科学基金;
关键词
Estimation; Solid modeling; Training; Optical fiber networks; Data models; Signal to noise ratio; Predictive models; NONLINEAR PROPAGATION; GN-MODEL; PREDICTION; QUALITY;
D O I
10.1364/JOCN.493053
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Machine learning has been introduced to estimate the quality of transmission (QoT) of lightpaths to meet the reliability of optical network transmission. In the early deployment phase of optical networks, it is difficult to collect enough training samples due to the insufficient lightpaths and monitoring equipment, which makes the estimation models inaccurate. Transfer learning (TL) has been demonstrated as a promising technology for improving the accuracy of estimation models. The main idea of the TL method is pre-training the QoT estimation model with the source domain samples, and then using a few target domain samples to fine-tune the models, which are named fine-tuning samples. However, there are many differences in sample distribution between the source and target domain networks, and more fine-tuning samples to train the TL models are required. Thus, how to improve the accuracy of TL-based QoT estimation models with few samples needs to be examined. This paper proposes a sample-distribution-matching-based transfer learning (SDMbTL) method to perform an accurate QoT estimation with fewer samples. The proposed SDMbTL method designs the sample distribution matching model to filter source domain samples to match the distribution of the target domain samples, which makes the pre-training model more suitable for target networks. We also propose three different matching algorithms to accommodate the discriminative features to be matched. The simulation results demonstrate that the performance of the proposed estimation models outperforms the traditional TL models, saving more than 28.5% of fine-tuning samples.
引用
收藏
页码:649 / 663
页数:15
相关论文
共 31 条
[1]   Survey on the Use of Machine Learning for Quality of Transmission Estimation in Optical Transport Networks [J].
Ayassi, Reda ;
Triki, Ahmed ;
Crespi, Noel ;
Minerva, Roberto ;
Laye, Maxime .
JOURNAL OF LIGHTWAVE TECHNOLOGY, 2022, 40 (17) :5803-5815
[2]   Comparison of domain adaptation and active learning techniques for quality of transmission estimation with small-sized training datasets [Invited] [J].
Azzimonti, Dario ;
Rottondi, Cristina ;
Giusti, Alessandro ;
Tornatore, Massimo ;
Bianco, Andrea .
JOURNAL OF OPTICAL COMMUNICATIONS AND NETWORKING, 2021, 13 (01) :A56-A66
[3]  
Chalapathy R, 2019, Arxiv, DOI arXiv:1802.06360
[4]   GNPy: an open source application for physical layer aware open optical networks [J].
Ferrari, Alessio ;
Filer, Mark ;
Balasubramanian, Karthikeyan ;
Yin, Yawei ;
Le Rouzic, Esther ;
Kundrat, Jan ;
Grammel, Gert ;
Galimberti, Gabriele ;
Curri, Vittorio .
JOURNAL OF OPTICAL COMMUNICATIONS AND NETWORKING, 2020, 12 (06) :C31-C40
[5]   ANN-Based Multi-Channel QoT-Prediction Over a 563.4-km Field-Trial Testbed [J].
Gao, Zhengguang ;
Yan, Shuangyi ;
Zhang, Jiawei ;
Mascarenhas, Marcus ;
Nejabati, Reza ;
Ji, Yuefeng ;
Simeonidou, Dimitra .
JOURNAL OF LIGHTWAVE TECHNOLOGY, 2020, 38 (09) :2646-2655
[6]   Extended Isolation Forest [J].
Hariri, Sahand ;
Kind, Matias Carrasco ;
Brunner, Robert J. .
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2021, 33 (04) :1479-1489
[7]   Towards converged, collaborative and co-automatic (3C) optical networks [J].
Ji, Yuefeng ;
Zhang, Jiawei ;
Wang, Xin ;
Yu, Hao .
SCIENCE CHINA-INFORMATION SCIENCES, 2018, 61 (12)
[8]   SVDD-based outlier detection on uncertain data [J].
Liu, Bo ;
Xiao, Yanshan ;
Cao, Longbing ;
Hao, Zhifeng ;
Deng, Feiqi .
KNOWLEDGE AND INFORMATION SYSTEMS, 2013, 34 (03) :597-618
[9]  
Liu CY, 2020, 2020 OPTICAL FIBER COMMUNICATIONS CONFERENCE AND EXPOSITION (OFC)
[10]   Performance studies of evolutionary transfer learning for end-to-end QoT estimation in multi-domain optical networks [Invited] [J].
Liu, Che-Yu ;
Chen, Xiaoliang ;
Proietti, Roberto ;
Ben Yoo, S. J. .
JOURNAL OF OPTICAL COMMUNICATIONS AND NETWORKING, 2021, 13 (04) :B1-B11