Title: Deep learning-based genetic algorithm for the robust hub allocation problem with discrete scenarios

Authors: Achraf Berrajaa

Addresses: Euromed Research Center, Euromed University of Fes, Fes, Morocco

Abstract: Over the last decade, big data have changed the work and research strategies of several areas, in particular the hub location problems (HLP). The HLP have been extended to handle uncertain data, giving rise to robust HLPs. In a RHLP with discrete scenarios, the unique set of requests is replaced by a set of discrete scenarios. In a robust optimisation approach, making appropriate decisions for all scenarios must be intelligent and optimal. The purpose of this study is to show that such problems can be solved in a reasonable computing time and with an intelligent solution, using a RNN based on GA to approximately solve the problem. The proposed RNN has been trained on a big dataset of 20,000 instances. The performances of the proposed RNN are very interesting such that the success rate is 91% and able to resolve large instances while the traditional approaches are fail to resolve them.

Keywords: robust HLP; discrete scenarios; deep learning; recurrent neural network; RNN; genetic algorithm.

DOI: 10.1504/IJLSM.2024.140398

International Journal of Logistics Systems and Management, 2024 Vol.48 No.4, pp.489 - 507

Received: 10 Jul 2021
Accepted: 29 Dec 2021
Published online: 07 Aug 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article