Chapter Six: Deep learning techniques for optical monitoring
Takahito Tanimura1; Takeshi Hoshida Fujitsu Limited, Kawasaki, Japan1Currently with Hitachi Ltd., Tokyo, Japan.
Abstract
Future optical networks will require automated network operation and management to accommodate their increasing operational complexity. A monitoring/perception of the status of the optical network is vital for realizing the network automation. Deep learning (DL)-based optical monitors that comprise digital coherent reception and deep neural networks (DNNs) are promising options because of their flexibility. In this chapter, we present the concept and basics of DL-based optical monitors in the training and inference modes and advanced techniques for enhancing DL-based ...
Get Machine Learning for Future Fiber-Optic Communication Systems now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.