Machine Learning Based Traffic-Aware Service Reconfiguration in Metropolitan Area Networks

With the development of 5G technology and the emergence of the large amount of traffic with various broadband services, the operation and resource scheduling of optical network are facing unprecedented challenges. In the metropolitan area network, the location where users access to the network changes in real time, causing that the tidal traffic in the network changes dynamically with the time. However, the network operators cannot make fast and flexible resource scheduling. Considering tidal traffic in the metropolitan area network, this paper proposes a traffic-aware service reconfiguration algorithm based on machine learning model.