Authors:
Pedro Henrique González
1
;
Luidi Gelabert Simonetti
2
;
Carlos Alberto de Jesus Martinhon
2
;
Philippe Yves Paul Michelon
3
and
Edcarllos Santos
2
Affiliations:
1
Fluminense Federal University and Université d’Avignon et des Pays de Vaucluse, Brazil
;
2
Fluminense Federal University, Brazil
;
3
Université d’Avignon et des Pays de Vaucluse, France
Keyword(s):
Network Design Problem, Heuristic, Local Branching, Bi-level Problem.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence and Decision Support Systems
;
Enterprise Information Systems
;
Operational Research
;
Problem Solving
Abstract:
Due to the constant development of society, increasing quantities of commodities have to be transported in large urban centers. Therefore, network design problems arise as tools to support decision-making, aiming to meet the need of finding efficient ways to perform the transportation of each commodity from its origin to its destination. This paper reviews a bi-level formulation, an one level formulation obtained by applying the complementary slackness theorem, Bellman’s optimality conditions and Big-M linearizing technique. A heuristic procedure is proposed, through combining a randomized constructive algorithm with a Relax-and-Fix heuristic to generate an initial solution. After that a Local Branching technique is applied to improve the constructed solution, so high quality solutions can be found. Besides that, our computational results are compared with the results found in the literature, showing the efficiency of the proposed method.