The use of cognition is a promising element for the control of heterogeneous optical networks. Not only are cognitive networks able to sense current network conditions and act according to them, but they also take into account the knowledge acquired through past experiences; that is, they include learning with the aim of improving performance. In this paper, we review the fundamentals of cognitive networks and focus on their application to the optical networking area. In particular, a number of cognitive network architectures proposed so far, as well as their associated supporting technologies, are reviewed. Moreover, several applications, mainly developed in the framework of the EU FP7 Cognitive Heterogeneous Reconfigurable Optical Network (CHRON) project, are also described.
© 2013 Optical Society of America
Original Manuscript: May 1, 2013
Revised Manuscript: July 20, 2013
Manuscript Accepted: July 20, 2013
Published: September 12, 2013
Ignacio de Miguel, Ramón J. Durán, Tamara Jiménez, Natalia Fernández, Juan Carlos Aguado, Rubén M. Lorenzo, Antonio Caballero, Idelfonso Tafur Monroy, Yabin Ye, Andrzej Tymecki, Ioannis Tomkos, Marianna Angelou, Dimitrios Klonidis, Antonio Francescon, Domenico Siracusa, and Elio Salvadori, "Cognitive Dynamic Optical Networks [Invited]," J. Opt. Commun. Netw. 5, A107-A118 (2013)