Machine Learning for Future Fiber-Optic Communication Systems

Machine Learning for Future Fiber-Optic Communication Systems

by Alan Tao Lau, Faisal Nadeem Khan
Released February 2022
Publisher(s): Academic Press
ISBN: 9780323852289

Read it now on the O’Reilly learning platform with a 10-day free trial.

O’Reilly members get unlimited access to books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.

Start your free trial

Book description

Machine Learning for Future Fiber-Optic Communication Systems provides a comprehensive and in-depth treatment of machine learning concepts and techniques applied to key areas within optical communications and networking, reflecting the state-of-the-art research and industrial practices. The book gives knowledge and insights into the role machine learning-based mechanisms will soon play in the future realization of intelligent optical network infrastructures that can manage and monitor themselves, diagnose and resolve problems, and provide intelligent and efficient services to the end users.

With up-to-date coverage and extensive treatment of various important topics related to machine learning for fiber-optic communication systems, this book is an invaluable reference for photonics researchers and engineers. It is also a very suitable text for graduate students interested in ML-based signal processing and networking.

  • Discusses the reasons behind the recent popularity of machine learning (ML) concepts in modern optical communication networks and the why/where/how ML can play a unique role
  • Presents fundamental ML techniques like artificial neural networks (ANNs), support vector machines (SVMs), K-means clustering, expectation-maximization (EM) algorithm, principal component analysis (PCA), independent component analysis (ICA), reinforcement learning, and more
  • Covers advanced deep learning (DL) methods such as deep neural networks (DNNs), convolutional neural networks (CNNs), recurrent neural networks (RNNs), and generative adversarial networks (GANs)
  • Individual chapters focus on ML applications in key areas of optical communications and networking

Table of contents

  1. Cover image
  2. Title page
  3. Table of Contents
  4. Copyright
  5. Dedication
  6. Contributors
  7. Preface
  8. Acknowledgments
  9. Chapter One: Introduction to machine learning techniques: An optical communication's perspective
    1. Abstract
    2. 1.1. Introduction
    3. 1.2. Supervised learning
    4. 1.3. Unsupervised learning
    5. 1.4. Reinforcement learning (RL)
    6. 1.5. Deep learning techniques
    7. 1.6. Future role of ML in optical communications
    8. 1.7. Online resources for ML algorithms
    9. 1.8. Conclusions
    10. Appendix 1.A.
    11. References
  10. Chapter Two: Machine learning for long-haul optical systems
    1. Abstract
    2. 2.1. Introduction
    3. 2.2. Application of machine learning in perturbation-based nonlinearity compensation
    4. 2.3. Application of machine learning in digital backpropagation
    5. 2.4. Outlook of machine learning in long-haul systems
    6. References
  11. Chapter Three: Machine learning for short reach optical fiber systems
    1. Abstract
    2. 3.1. Introduction to optical systems for short reach
    3. 3.2. Deep learning approaches for digital signal processing
    4. 3.3. Optical IM/DD systems based on deep learning
    5. 3.4. Implementation on a transmission link
    6. 3.5. Outlook
    7. References
  12. Chapter Four: Machine learning techniques for passive optical networks
    1. Abstract
    2. 4.1. Background
    3. 4.2. The validation of NN effectiveness
    4. 4.3. NN for nonlinear equalization
    5. 4.4. End to end deep learning for optimal equalization
    6. 4.5. FPGA implementation of NN equalizer
    7. 4.6. Conclusions and perspectives
    8. References
  13. Chapter Five: End-to-end learning for fiber-optic communication systems
    1. Abstract
    2. Acknowledgements
    3. 5.1. Introduction
    4. 5.2. End-to-end learning
    5. 5.3. End-to-end learning for fiber-optic communication systems
    6. 5.4. Gradient-free end-to-end learning
    7. 5.5. Conclusion
    8. References
  14. Chapter Six: Deep learning techniques for optical monitoring
    1. Abstract
    2. Acknowledgement
    3. 6.1. Introduction
    4. 6.2. Building blocks of deep learning-based optical monitors
    5. 6.3. Deep learning-based optical monitors
    6. 6.4. Tips for designing DNNs for DL-based optical monitoring
    7. 6.5. Experimental verifications
    8. 6.6. Future direction of data-analytic-based optical monitoring
    9. 6.7. Summary
    10. References
  15. Chapter Seven: Machine Learning methods for Quality-of-Transmission estimation
    1. Abstract
    2. 7.1. Introduction
    3. 7.2. Classification and regression models for QoT estimation
    4. 7.3. Active and transfer learning approaches for QoT estimation
    5. 7.4. On the integration of ML in optimization tools
    6. 7.5. Illustrative numerical results
    7. 7.6. Future research directions and challenges
    8. 7.7. Conclusion
    9. References
  16. Chapter Eight: Machine Learning for optical spectrum analysis
    1. Abstract
    2. List of acronyms
    3. 8.1. Introduction
    4. 8.2. Feature-based spectrum monitoring
    5. 8.3. Residual-based spectrum monitoring
    6. 8.4. Monitoring of filterless optical networks
    7. 8.5. Concluding remarks and future work
    8. References
  17. Chapter Nine: Machine learning and data science for low-margin optical networks
    1. Abstract
    2. 9.1. The shape of networks to come
    3. 9.2. Current QoT margin taxonomy and design
    4. 9.3. Generalization of optical network margins
    5. 9.4. Large scale assessment of margins and their time variations in a deployed network
    6. 9.5. Trade-off between capacity and availability
    7. 9.6. Data-driven rate adaptation for automated network upgrades
    8. 9.7. Machine learning for low-margin optical networks
    9. 9.8. Conclusion
    10. References
  18. Chapter Ten: Machine learning for network security management, attacks, and intrusions detection
    1. Abstract
    2. Acknowledgements
    3. 10.1. Physical layer security management
    4. 10.2. Machine learning techniques for security diagnostics
    5. 10.3. Accuracy of ML models in threat detection
    6. 10.4. Runtime complexity of ML models
    7. 10.5. Interpretability of ML models
    8. 10.6. Open challenges
    9. 10.7. Conclusion
    10. References
  19. Chapter Eleven: Machine learning for design and optimization of photonic devices
    1. Abstract
    2. 11.1. Introduction
    3. 11.2. Deep neural network (DNN) models
    4. 11.3. Nanophotonic power splitter
    5. 11.4. Metasurfaces and plasmonics
    6. 11.5. Other types of optical devices
    7. 11.6. Discussion
    8. 11.7. Conclusion
    9. References
  20. Index

Product information

  • Title: Machine Learning for Future Fiber-Optic Communication Systems
  • Author(s): Alan Tao Lau, Faisal Nadeem Khan
  • Release date: February 2022
  • Publisher(s): Academic Press
  • ISBN: 9780323852289