OFC: Machine learning for the physical & network layers

Point of contact

Summary

Machine learning (ML) and artificial intelligence (AI) techniques are being praised as a new innovation direction to transform future optical communication systems. Signal processing paradigms based on ML (reinforcement learning, artificial neural networks,…) are being considered to solve critical problems that cannot be easily tackled using conventional approaches. Recent applications include nonlinear transmission systems to mitigate non-linear phase noise, network planning and performance prediction, cross-layer network optimizations for software-defined networks, and autonomous and reliable self-healing networks. In this topic, our goal is to comprehend the true potential of ML in optical fiber communication systems by studying and focusing on problems in otical transmission and networking where ML can be useful.

Keywords

Machine learning, autonomous optical fiber networks, network planning, performance prediction

Researchers involved or interested

  • Cédric Ware, Telecom ParisTech
  • Mansoor Yousefi, Telecom ParisTech
  • Mounia Lourdiane, Telecom SudParis
  • Catherine Lepers, SAMOVAR – Telecom SudParis, catherine-lepers@telecom-sudparis.eu

A few references

  • Danish Rafique and Luis Velasco, “Machine Learning for Network Automation: Overview, Architecture, and Applications [Invited Tutorial],” J. Opt. Commun. Netw. 10, D126-D143 (2018)
  • F. Musumeci et al., “An Overview on Application of Machine Learning Techniques in Optical Networks,” in IEEE Communications Surveys & Tutorials, vol. 21, no. 2, pp. 1383-1408, Secondquarter 2019, doi: 10.1109/COMST.2018.2880039
  • B. Karanov et al., “End-to-End Deep Learning of Optical Fiber Communications,” in Journal of Lightwave Technology, vol. 36, no. 20, pp. 4843-4855, 15 Oct.15, 2018, doi: 10.1109/JLT.2018.2865109.
  • Faisal Nadeem Khan et al., “Chapter 21 – Machine learning methods for optical communication systems and networks,” Optical Fiber Telecommunications VII, Academic Press (2020), pp. 921-978.