This special issue of JOCN will focus on new applications of machine learning and data analytics for the design and operation of next-generation optical communication systems and networks. The increasing complexity of networks combined with the growing desirability for dynamic services and adaptable networks have led to a need for new techniques to automate and optimize network operation. Machine learning allows the inference of useful network characteristics that cannot be easily or directly measured. This offers operational advantages by allowing the network to 'draw conclusions' and react autonomously.
There are a range of applications that can take advantage of a cognitive optical network. For example, machine learning potentially enables pro-active autonomous virtual topology reconfiguration based on network state, and may provide rapid and accurate estimation of the quality of transmission of a new connection. Cognitive techniques may be utilized in adaptable networks to adjust operational parameters to optimize transport system capacity and transparency. With regard to network management, artificial neural networks have been proposed for optical performance monitoring, predictive methodologies may be used to anticipate failures and pro-actively shift traffic, and anomaly detection potentially can be used to detect security breaches in the optical layer.
The Special Issue may include a small number of tutorial articles on the current state of machine learning and data analytics in optical networks. However, the focus of the issue is on novel applications of machine learning and new cognitive techniques, with the goal of probing their true benefits in the context of optical networks and identifying realistic and implementable solutions. Papers shall be written considering the readership might not be completely familiar with some of the methodological/mathematical aspects.
The scope of the special issue includes but is not limited to the following topics:
Submissions to the special issue should be prepared according to the usual standards for the Journal of Optical Communications and Networking and will undergo the normal peer review process. Manuscripts must be uploaded through OSA's online submission system specifying from the Feature Issue drop-down menu that the manuscript is for the issue on Machine Learning for Optical Communications and Networking.
Massimo Tornatore, Politecnico di Milano, Italy
Martin Birk, AT&T, United States
Alan P. T. Lau, Hong Kong Polytechnic University, China
Qiong Zhang, Fujitsu Laboratories of America, Inc., United States
Darko Zibar, Technical University of Denmark, Denmark