Customized genetic algorithm for facility allocation using p-median

The p-median problem is classified as a NP-hard problem, which demands a long time for solution. To increase the use of the method in public management, commercial, military and industrial applications, several heuristic methods has been proposed in literature. In this work, we propose a customized Genetic Algorithm for solving the p-median problem, and we present its evaluation using benchmark problems of OR-library. The customized method combines parameters used in previous studies and introduces the evolution of solutions in stationary mode for solving PMP problems. The proposed Genetic Algorithm found the optimum solution in 37 of 40 instances of p-median problem. The mean deviation from the optimal solution was 0.002% and the mean processing time using CPU core i7 was 17.7s.

---

1. This research was financial supported by Samsung Electronica da Amazonia Ltda, under the terms of the Brazilian Federal Law number 8.387/91, through an agreement signed with Center for R&D in Electronic and Information Technology- CETELI/UFAM.

---

2. Track 1: Artificial Intelligence and Applications

---

3. Technical Session: 12th International Workshop on Computational Optimization

---

4. Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2020).