Data-Driven Bandwidth Allocation in EONs

We investigate periodically and dynamically reconfiguring elastic optical networks (EONs) utilizing predictive bandwidth allocation models found by applying reinforcement learning. These models aim at efficiently utilizing the network resources so that the quality-of-service (QoS) requirements are met, in networks where the traffic is evolving in an uncertain way.© 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. T. Panayiotou, G. Ellinas, "Data-Driven Bandwidth Allocation in EONs" 2018 IEEE Photonics in Switching and Computing (PSC) , September 201