A constraints satisfaction approach to the robust spanning tree problem with interval data

Abstract. Robust optimization is one of the fundamental approaches to deal with uncertainty in combinatorial optimization. This paper considers the robust span-ning tree problem with interval data, which arises in a variety of telecommunica-tion applications. It proposes a constraint satisfaction approach using a combina-torial lower bound, a pruning component that removes infeasible and suboptimal edges, as well as a search strategy exploring the most uncertain edges first. The resulting algorithm is shown to produce very dramatic improvements over the mathematical programming approach of Yaman et al. and to enlarge consider-ably the class of problems amenable to effective solutions.