A supervised learning-driven heuristic for solving the facility location and production planning problem

In this study, we propose a supervised learning-driven (SLD) heuristic to solve the capacitated facility lo-cation and production planning (CFLPP) problem. Using the solution values derived from linear program-ming relaxation, Dantzig-Wolfe decomposition, and column generation as features, the SLD heuristic uses a supervised learning approach (i.e., naive Bayes) to derive an offline-learned oracle on the optimal solu-tion patterns. The oracle and the incumbent feasible solution obtained by a time-oriented decomposition method (i.e., relax-and-fix) are then used to guide a sampling procedure to iteratively create numerous smaller-sized subproblems, which are solved by the relax-and-fix method to gradually improve the solu-tion for the CFLPP problem. Computational results show that the SLD heuristic achieves better solution qualities than the commercial CPLEX solver and several state-of-the-art methods.(c) 2021 Elsevier B.V. All rights reserved.

Automated summary

In this study, a supervised learning-driven heuristic is proposed to solve the capacitated facility location and production planning problem. The heuristic uses solution values from linear programming relaxation, Dantzig-Wolfe decomposition, and column generation as features and applies a naive Bayes approach to derive an offline-learned oracle. Computational results show that the proposed heuristic outperforms the commercial CPLEX solver and several state-of-the-art methods in terms of solution quality.