Application of machine learning techniques to optical communication systems and networks

摘要

This TFM reviews the application of machine learning techniques in optical communication systems and networks. In addition, it studies and compares the characteristics of various machine learning methods, such as: support vector machines, logistic regression, decision trees and random forests, to predict the quality of transmission when using optical circuits in wavelength routed optical communication networks. The models developed in this TFM offer better performance than previous proposals, mainly in terms of computing time, making possible its use in online mode even in highly dynamic networks, in addition to being simpler.