Digital-twin-assisted meta learning for soft-failure localization in ROADM-based optical networks

被引:1
|
作者
Wang, Ruikun [1 ,2 ]
Zhang, Jiawei [1 ]
Gu, Zhiqun [1 ]
Ibrahimi, Memedhe [2 ]
Zhang, Bojun [1 ]
Musumeci, Francesco [2 ]
Tornatore, Massimo [2 ]
Ji, Yuefeng [1 ]
机构
[1] Beijing Univ Posts & Telecommun, State Key Lab Informat Photon & Opt Commun, Beijing, Peoples R China
[2] Politecn Milan, Milan, Italy
基金
中国国家自然科学基金;
关键词
Optical fiber networks; Training; Location awareness; Task analysis; Data models; Metalearning; Stimulated emission;
D O I
10.1364/JOCN.517551
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Reconfigurable optical add/drop multiplexer (ROADM) nodes are evolving towards high-degree architectures to support growing traffic and enable flexible network connectivity. Due to the complex composition of high-degree ROADMs, soft failures may occur between both inter- and intra-node components, like wavelength selective switches and fiber spans. The intricate ROADM structure significantly contributes to the challenge of localizing inter-/intra-node soft failures in ROADM-based optical networks. Machine learning (ML) has shown to be a promising solution to the problem of soft-failure localization, enabling network operators to take accurate and swift measures to overcome such challenges. However, data scarcity is a main hindrance when using ML for soft-failure localization, especially in the complex scenario of inter- and intra-node soft failures. In this work, we propose a digital-twin-assisted meta-learning framework to localize inter-/intra-node soft failures with limited samples. In our proposed framework, we construct several mirror models using a digital twin of the physical optical network and then generate multiple training tasks. These training tasks serve as pretraining data for the meta learner. Then, we use real data for fine-tuning and testing of the meta learner. The proposed framework is compared with the rule-based reasoning method, transfer-learning-based method, and artificial-neural-network-based method with no pretraining. Experimental results indicate that the proposed framework improves localization accuracy by over 15%, 33%, and 54%, on average, compared to benchmark approaches, respectively.
引用
收藏
页码:C11 / C19
页数:9
相关论文
共 14 条
  • [1] Demonstration of ML-Assisted Soft-Failure Localization Based on Network Digital Twins
    Mayer, Kayol S.
    Pinto, Rossano P.
    Soares, Jonathan A.
    Arantes, Dalton S.
    Rothenberg, Christian E.
    Cavalcante, Vinicius
    Santos, Leonardo L.
    Moraes, Filipe D.
    Mello, Darli A. A.
    [J]. JOURNAL OF LIGHTWAVE TECHNOLOGY, 2022, 40 (14) : 4514 - 4520
  • [2] Learning from the Optical Spectrum: Soft-Failure Identification and Localization
    Velasco, Luis
    Shariati, Behnam
    Vela, Alba P.
    Comellas, Jaume
    Ruiz, Marc
    [J]. 2018 OPTICAL FIBER COMMUNICATIONS CONFERENCE AND EXPOSITION (OFC), 2018,
  • [3] Machine learning framework for timely soft-failure detection and localization in elastic optical networks
    Behera, Sadananda
    Panayiotou, Tania
    Ellinas, Georgios
    [J]. JOURNAL OF OPTICAL COMMUNICATIONS AND NETWORKING, 2023, 15 (10) : E74 - E85
  • [4] Machine-Learning-Based Soft-Failure Detection and Identification in Optical Networks
    Shahkarami, Shahin
    Musumeci, Francesco
    Cugini, Filippo
    Tornatore, Massimo
    [J]. 2018 OPTICAL FIBER COMMUNICATIONS CONFERENCE AND EXPOSITION (OFC), 2018,
  • [5] Suspect Fault Screening Assisted Graph Aggregation Network for Intra-/Inter-Node Failure Localization in ROADM-based Optical Networks
    Wang, Ruikun
    Zhang, Jiawei
    Yan, Shuangyi
    Zeng, Chuidian
    Yu, Hao
    Gu, Zhiqun
    Zhang, Bojun
    Taleb, Tarik
    Ji, Yuefeng
    [J]. 2022 EUROPEAN CONFERENCE ON OPTICAL COMMUNICATION (ECOC), 2022,
  • [6] Suspect fault screen assisted graph aggregation network for intra-/inter-node failure localization in ROADM-based optical networks
    Wang, Ruikun
    Zhang, Jiawei
    Yan, Shuangyi
    Zeng, Chuidian
    Yu, Hao
    Gu, Zhiqun
    Zhang, Bojun
    Taleb, Tarik
    Ji, Yuefeng
    [J]. JOURNAL OF OPTICAL COMMUNICATIONS AND NETWORKING, 2023, 15 (07) : C88 - C99
  • [7] PCA-assisted Fuzzy Clustering Approach for Soft-Failure Detection in Optical Networks
    Ribeiro, A. N.
    Sales, R. F.
    Lobato, F. R.
    Costa, J. C. W. A.
    Silva, M. F.
    Sgambelluri, A.
    Valcarenghi, L.
    Wosinska, L.
    [J]. PROCEEDINGS OF THE 2024 INTERNATIONAL CONFERENCE ON OPTICAL NETWORK DESIGN AND MODELING, ONDM 2024, 2024,
  • [8] Confidentiality-preserving machine learning algorithms for soft-failure detection in optical communication networks
    Silva, Moises Felipe
    Sgambelluri, Andrea
    Pacini, Alessandro
    Paolucci, Francesco
    Green, Andre
    Mascarenas, David
    Valcarenghi, Luca
    [J]. JOURNAL OF OPTICAL COMMUNICATIONS AND NETWORKING, 2023, 15 (08) : C212 - C222
  • [9] Soft-failure Identification and Localization Method Based on Received Optical Signal Quality and Repeater Nodes' Performance
    Yamamoto, Hiroshi
    Watanabe, Kouhei
    Date, Hiroki
    Shimazaki, Daisaku
    Fukuchi, Yutaka
    Maeda, Hideki
    [J]. 2023 OPTICAL FIBER COMMUNICATIONS CONFERENCE AND EXHIBITION, OFC, 2023,
  • [10] Experimental investigation of machine-learning-based soft-failure management using the optical spectrum
    Kruse, Lars E.
    Kuehl, Sebastian
    Dochhan, Annika
    Pachnicke, Stephan
    [J]. JOURNAL OF OPTICAL COMMUNICATIONS AND NETWORKING, 2024, 16 (02) : 94 - 103