Search

Problem definition: We study efficient exact solution approaches to solve chance-constrained multicommodity network design problems under demand uncertainty, an important class of network design problems. The chance constraint requires us to construct a network that meets future commodity demand sufficiently often, which makes the problem challenging to solve. Methodology/results: We develop a solution approach based on Benders' decomposition, and accelerate the approach with valid inequalities and cut strengthening. We particularly investigate the effects of different subproblem formulations on the strength of the resulting feasibility cuts. We propose a new formulation that we term FlowMIS, and investigate its properties. Additionally, we numerically show that FlowMIS outperforms standard formulations: in our complete solution approach with all enhancements enabled, FlowMIS solves 67 out of 120 solved instances the fastest, with an average speed-up of 2.0x over a basic formulation. Implications: FlowMIS generates strong feasibility cuts tailored to subproblems with a network flow structure. This results in reduced solution times for existing decomposition-based algorithms in the context of network design, and the ability to solve larger problems.

Inspired by its success for their continuous counterparts, the standard approach to deal with mixed-integer recourse (MIR) models under distributional uncertainty is to use distributionally robust optimization (DRO). We argue, however, that this modeling choice is not always justified, since DRO techniques are generally computationally extremely challenging when integer decision variables are involved. That is why we propose a fundamentally different approach for MIR models under distributional uncertainty aimed at obtaining models with improved computational tractability. For the special case of simple integer recourse (SIR) models, we show that tractable models can be obtained by pragmatically selecting the uncertainty set. Here, we consider uncertainty sets based on the Wasserstein distance and also on generalized moment conditions. We compare our approach with standard DRO and discuss potential generalizations of our ideas to more general MIR models. An important side-result of our analysis is the derivation of performance guarantees for convex approximations of SIR models. In contrast with the literature, these error bounds are not only valid for continuous distribution, but hold for any distribution., Comment: 35 pages, 5 figures

We consider two-stage recourse models in which the second-stage problem has integer decision variables and uncertainty in the second-stage cost vector, technology matrix, and the right-hand side vector. Such mixed-integer recourse models are typically non-convex and thus hard to solve. There exist convex approximations of these models with accompanying error bounds. However, it is unclear how these error bounds depend on the distributions of the second-stage cost vector $q$. In fact, the only error bound that is known hinges on the assumption that $q$ has a finite support. In this paper, we derive parametric error bounds whose dependence on the distribution of $q$ is explicit and that hold for any distribution of $q$, provided it has a finite expected $\ell_1$-norm. We find that the error bounds scale linearly in the expected value of the $\ell_1$-norm of $q$., Comment: 8 pages

Multi-stage problems with uncertain parameters and integer decisions variables are among the most difficult applications of robust optimization (RO). The challenge in these problems is to find optimal here-and-now decisions, taking into account that the wait-and-see decisions have to adapt to the revealed values of the uncertain parameters. Postek and den Hertog (2016) and Bertsimas and Dunning (2016) propose to solve these problems by constructing piecewise constant decision rules by adaptively partitioning the uncertainty set. The partitions of this set are iteratively updated by separating so-called critical scenarios of the uncertain parameters. Both references present methods for identifying these critical scenarios. However, these methods are most suitable for problems with continuous decision variables and many uncertain constraints. In particular, they are not able to identify informative sets of critical scenarios for integer problems with uncertainty in the objective function only. In this note, we address this shortcoming of existing methods by introducing a general critical scenario detection method for mixed-integer adjustable robust optimization problems that is based on the branch-and-bound tree used to solve the corresponding static problem. Numerical experiments on a route planning problem show that our general-purpose method outperforms the problem-specific approach of Postek and den Hertog (2016).