On the efficient optimization of unicast, anycast and multicast flows in survivable elastic optical networks

Abstract

The paper investigates efficient allocation of three types of flows (unicast, anycast, multicast) in elastic optical network with dedicated path protection. We model the problem as an integer linear programming and propose efficient solution methods: greedy randomized algorithm (GRA) and column generation (CG)-based approach implemented in two versions, which differ in the method used to find a final problem solution for the selected columns. Then, we evaluate in detail methods efficiency with respect to four reference algorithms. What is more, for CG-based methods we use five different algorithms to find initial sets of columns and, by these means, evaluate how the quality of these methods influences the efficiency of CG-based approaches. The simulation results show that the proposed GRA significantly outperforms reference greedy methods and finds very good solutions (the average gap to optimal result was not higher than 13.4%). The CG-based methods allow to further improve results and obtain solutions very close to optimal ones (for the best CG-based version, the highest average gap to optimal result was 2.1%). Moreover, the results show that the traffic pattern influences the algorithms performance. The methods perform the best for scenarios with high amount of multicast volume while high anycast volume brings the most difficult problem instances. Eventually, the study reveals that the efficiency of CG-based methods depends strongly on the quality of initial columns as well as on the method used to find final solution for the selected columns.