Channel allocation in elastic optical networks using traveling salesman problem algorithms

Abstract

Elastic optical networks have been proposed to support high data-rates in metro and core networks. However, frequency allocation of the channels (i.e., channel ordering) in such networks is a challenging problem. This requires arrangement of the optical channels within the frequency grid with the objective of ensuring a minimum signal-to-noise ratio (SNR). An optimal arrangement results in the highest SNR margin for the entire network. However, searching for the optimal arrangement requires an exhaustive search through all possible arrangements (permutations) of the channels. The search space increases exponentially with the number of channels. This discourages an algorithm employing exhaustive search for the optimal frequency allocation. We utilize the Gaussian noise (GN) model to formulate the frequency allocation (channel ordering) problem as a variant of the traveling salesman problem (TSP) using graph theory. Thereafter, we utilize graph-theoretic tools for TSP from the existing literature to solve the channel ordering problem. Performance figures obtained for the proposed scheme is illustrated to be marginally inferior to the optimal search (through all possible permutations) and outperforms any random allocation scheme. Moreover, the proposed scheme is implementable for a scenario with a large number of channels. In comparison, exhaustive search with the GN model and splitstep Fourier method simulations are shown to be feasible for a small number of channels only. It is also illustrated that the SNR reduces with an increase in bandwidth when the frequency separation is high.