Abstract
The logistic network design is an abstract optimization problem which, under the assumption of minimal cost, seeks the optimal configuration of infrastructures and facilities of the supply chain based on customer demand. Key economic decisions are taken about the location, number, and size of manufacturing facilities and warehouses base on the optimal solution to this problem. Therefore, improvements in the methods to address this question, which is known to be in the NP-hard complexity class, would have relevant financial consequences. Here, we implement in the D-Wave quantum annealer a hybrid classical-quantum annealing algorithm. The cost function with constraints is translated to a spin Hamiltonian, whose ground state encodes the searched result. As a benchmark, we measure the accuracy of result for a set of paradigmatic problems against the optimal published solutions (the error is on average below $1\%$), and the performance is compared against the classical algorithm, showing a remarkable reduction in the number of iterations. This work shows that, even still far from useful quantum supremacy, state-of-the-art quantum annealers may codify and solve relevant supply-chain problems.

This publication has 28 references indexed in Scilit: