The Internet has shown exponential growth in the last decade, generating that users demand solutions to the requirements instantly. These requirements constitute the main problem related to the performance and characterization of the access and aggregation network infrastructure. Among the promising technologies are optical networks, their characteristics in capacity, quality of service and performance allow to support the traffic generated by future applications and technologies such as high-definition video, 5G networks and ultra-definition transmissions. Today, the implementation of all-optical networks presents several challenges such as: device maturity, optical storage buffers, optical packet switching, lack of effective network administration and management methods, and high costs. These limitations have delayed the development of fully optical networks, promoting research into elastic optical networks (EON), which dynamically adjust their resources according to the requirements of each demand. This research addresses the benefits in the use of elastic optical networks as support in the transport of the increasing volume of traffic, supported with machine learning techniques to face the problems of routing, spectrum allocation, modulation format and core selection. Providing a technological vision for the exploitation of the infrastructure that ensures completely optical switching and routing processes, optimizing resources based on demands.