A Survey on Machine and Deep Learning for Optical Communications

The ever-growing complexity of optical communication systems and networks demands sophisticated methodologies to extract meaningful insights from vast amounts of heterogeneous data. Machine learning (ML) and deep learning (DL) have emerged as frontrunners in this domain, offering a transformative approach to data analysis and enabling automated self-configuration in optical communication systems. The adoption of ML and DL in optical communication is driven by the exponential increase in system and link complexity, stemming from the introduction of numerous adjustable and interdependent parameters. This is particularly evident in areas like coherent transceivers, advanced digital signal processing, optical performance monitoring, cross-layer network optimizations, and nonlinearity compensation. While the potential benefits of ML and DL are immense, the extent to which these methods can revolutionize optical communication remains largely unexplored. Additionally, many ML and DL algorithms have yet to be deployed in this field, highlighting the nascent nature of this research area.