Lifelong QoT prediction: an adaptation to real-world optical networks

Qihang Wang, Zhuojun Cai, and Faisal Nadeem Khan

Author Information

Author Affiliations

Qihang Wang,Zhuojun Cai,and Faisal Nadeem Khan^*

Tsinghua Shenzhen International Graduate School, Tsinghua University, University Town of Shenzhen, Nanshan District, Shenzhen 518055, China

^*Corresponding author:faisal.khan@sz.tsinghua.edu.cn

ORCID

Faisal NadeemKhan

https://orcid.org/0000-0002-3053-974X

Find other works by these authors

• Q Wang
• Z Cai
• F Khan

Your library or personal account may give you access

• Abstract
• Full Article

• Figures (10)
• Tables (1)
• Equations (10)
• References (46)
• Cited By
• Back to Top

Abstract

Predicting the quality of transmission (QoT) is a critical task in the management and optimization of modern fiber-optic networks. Traditional machine learning (ML) QoT prediction models, typically trained on pre-collected datasets, are designed to make long-term predictions once deployed. However, this static training strategy often falls short in the face of time-dependent network evolution and variations. We identify the root cause of these shortcomings as shifts in data distribution, which are not accounted for in conventional static models. In response to these challenges, we propose an online continual learning pipeline that is specifically designed for stable QoT prediction in optical networks. This pipeline directly addresses the problem of distribution shifts by continuously updating the prediction model in response to real-time network data. We explore and compare various strategies within this framework and demonstrate that the integration of the adaptive retraining strategy and the regularized online continual learning algorithm (OCL-REG) significantly enhances the QoT prediction stability while optimizing the resource efficiency. OCL-REG demonstrates superior adaptability and stability, achieving an average cumulative mean squared error (C-MSE) of 0.19 on a testbench with a data distribution shift sequence containing 1000 batches. Moreover, the OCL-REG model requires fewer samples for adaptation, averaging around 107 samples, compared to the conventional retraining strategy, which requires an average of 253 samples. Our approach presents a paradigm shift in QoT prediction, moving from a static to a dynamic, lifelong learning model that is more attuned to the evolving realities of real fiber-optic networks.

© 2024 Optica Publishing Group. All rights, including for text and data mining (TDM), Artificial Intelligence (AI) training, and similar technologies, are reserved.

Domain adversarial adaptation framework for few-shot QoT estimation in optical networks

Zhuojun Cai, Qihang Wang, Yubin Deng, Peng Zhang, Gai Zhou, Yang Li, and Faisal Nadeem Khan
J. Opt. Commun. Netw.16(11) 1133-1144 (2024)

Invariant convolutional neural network for robust and generalizable QoT estimation in fiber-optic networks

Qihang Wang, Zhuojun Cai, Alan Pak Tao Lau, Yang Li, and Faisal Nadeem Khan
J. Opt. Commun. Netw.15(7) 431-441 (2023)

Evolutionary neuron-level transfer learning for QoT estimation in optical networks

Yuhang Zhou, Zhiqun Gu, Jiawei Zhang, and Yuefeng Ji
J. Opt. Commun. Netw.16(4) 432-448 (2024)

Model transfer of QoT prediction in optical networks based on artificial neural networks

Jiakai Yu, Weiyang Mo, Yue-Kai Huang, Ezra Ip, and Daniel C. Kilper
J. Opt. Commun. Netw.11(10) C48-C57 (2019)

On the generalization of cognitive optical networking applications using composable machine learning

Hanyu Gao, Xiaoliang Chen, Chao Lu, and Zhaohui Li
J. Opt. Commun. Netw.16(6) 631-643 (2024)

Cited By

You do not have subscription access to this journal. Cited by links are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

Figures (10)

You do not have subscription access to this journal. Figure files are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

Tables (1)

You do not have subscription access to this journal. Article tables are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

Equations (10)

You do not have subscription access to this journal. Equations are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription