Computational intelligence techniques have appeared as efficient alternatives to solve complex problems, such as in optimization of multi-objective problems. These techniques have been used to solve hard problems in optical networks, such as the impairment-aware routing and wavelength assignment problem, the design of the physical and the logical topology, and the placement of high cost devices along the network where necessary, such as regenerators and wavelength converters. This paper presents some examples of the use of evolutionary computation, swarm intelligence and neurocomputing to solve these optical network problems.

Date Published: 5 February 2013
PDF: 8 pages
Proc. SPIE 8646, Optical Metro Networks and Short-Haul Systems V, 86460D (5 February 2013); doi: 10.1117/12.2008321

Published in SPIE Proceedings Vol. 8646:
Optical Metro Networks and Short-Haul Systems V
Werner Weiershausen; Benjamin B. Dingel; Achyut K. Dutta; Atul K. Srivastava, Editor(s)