Literature review on the use of machine learning to authomatize optical networks, either for controlling, either for restoration,

Literature review on the use of machine learning to authomatize optical networks, either for controlling, either for restoration, In today’s world, the Quantity of Data that can be recovered from communications networks is enormously high and diverse. Progressive exact tools are needed to extract valuable information from this large set of network traffic traces. e.g., data regarding user’s behavior, Network alarms, Traffic traces, Signal quality indicators, etc. Advanced mathematical tools are needed to remove important information from this data and take decisions denote to the proper functioning of the networks from the network generated data. In specific, Machine Learning (ML) is viewed as a probable methodological area to achieve network data analysis and enable, for example., Automatized network self-configuration and fault management. The implementation of ML methods in Optical Communication networks is motivated by the huge growth of network complication in the optical networks in the last few years. In this thesis I categorize and describe relevant studies dealing with the claims of ML to optical communications and networking. Optical networks and systems are facing an extraordinary growth in terms of complexity due to the introduction of a large number of variable parameters like Modulation format, routing configurations, coding schemes, etc. Mainly due to the adoption of logical transmission and reception technologies, Advanced digital signal processing and due to the existence of nonlinear properties in optical fiber systems. Though a huge number of research papers related to this area have been appeared in the last few years, the application of ML to optical Communication and networking is still in its early stages. To motivate further work in this area, in this thesis I conclude new possible Research directions.