Machine Learning Techniques in Optical Networks: A Systematic Mapping Study

Abstract

During the last decade, optical networks have become 'smart networks'. Software-defined networks, software-defined optical networks, and elastic optical networks are some emerging technologies that provide a basis for promising innovations in the functioning and operation of optical networks. Machine learning algorithms are providing the possibility to develop this promising study area. Since machine learning can learn from a large amount of data available from the network elements. They can find a suitable solution for any environment and thus create more dynamic and flexible networks that improve the user experience. This paper performs a systematic mapping that provides an overview of machine learning in optical networks, identifies opportunities, and suggests future research lines. The study analyzed 96 papers from the 841 publications on this topic to find information about the use of machine learning techniques to solve problems related to the functioning and operation of optical networks. It is concluded that supervised machine learning techniques are mainly used for resource management, network monitoring, fault management, and traffic classification and prediction of an optical network. However, specific challenges need to be solved to successfully deploy this type of method in real communication systems since most of the research has been carried out in controlled experimental environments.