Two Use Cases of Machine Learning for SDN-Enabled IP/Optical Networks: Traffic Matrix Prediction and Optical Path Performance Prediction

TL;DR

This paper explores two machine learning applications in SDN-enabled IP/Optical networks: traffic prediction for resource management and optical performance prediction for network migration, demonstrating cost savings and improved robustness.

Contribution

It introduces novel ML-based methods for traffic and optical performance prediction in SDN-enabled IP/Optical networks, enhancing resource management and network migration strategies.

Findings

ML enables accurate traffic flow prediction for resource optimization

Optical performance prediction supports network migration without detailed optical parameters

Prototypes demonstrate cost savings and robustness improvements

Abstract

We describe two applications of machine learning in the context of IP/Optical networks. The first one allows agile management of resources at a core IP/Optical network by using machine learning for short-term and long-term prediction of traffic flows and joint global optimization of IP and optical layers using colorless/directionless (CD) flexible ROADMs. Multilayer coordination allows for significant cost savings, flexible new services to meet dynamic capacity needs, and improved robustness by being able to proactively adapt to new traffic patterns and network conditions. The second application is important as we migrate our metro networks to Open ROADM networks, to allow physical routing without the need for detailed knowledge of optical parameters. We discuss a proof-of-concept study, where detailed performance data for wavelengths on a current flexible ROADM network is used for machine learning to predict the optical performance of each wavelength. Both applications can be efficiently implemented by using a SDN (Software Defined Network) controller.