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.