Robust branch-cut-and-price for the Capacitated Minimum Spanning Tree problem over a large extended formulation

Authors:
Eduardo Uchoa;Ricardo Fukasawa;Jens Lysgaard;Artur Pessoa;Marcus Poggi de Aragão;Diogo Andrade
Affiliations:
Universidade Federal Fluminense, Departamento de Engenharia de Produçao, Niterói, Brazil;GeorgiaTech, H. Milton Stewart School of Industrial and Systems Engineering, Atlanta, GA, USA;Aarhus School of Business, Department of Business Studies, Aarhus, GA, Denmark;Universidade Federal Fluminense, Departamento de Engenharia de Produçao, Niterói, Brazil;PUC Rio de Janeiro, Departamento de Informática, Rio de Janerio, GA, Brazil;Rutgers University, RUTCOR, Piscataway, NJ, USA
Venue:
Mathematical Programming: Series A and B
Year:
2007

Citing 0
Cited 5

On a Generalization of the Master Cyclic Group Polyhedron

IPCO '07 Proceedings of the 12th international conference on Integer Programming and Combinatorial Optimization
GRASP with hybrid heuristic-subproblem optimization for the multi-level capacitated minimum spanning tree problem

Journal of Heuristics
A robust branch-cut-and-price algorithm for the heterogeneous fleet vehicle routing problem

WEA'07 Proceedings of the 6th international conference on Experimental algorithms
Leveraging saving-based algorithms by master-slave genetic algorithms

Engineering Applications of Artificial Intelligence
Improved lower bounds for the Split Delivery Vehicle Routing Problem

Operations Research Letters

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a robust branch-cut-and-price algorithm for the Capacitated Minimum Spanning Tree Problem (CMST). The variables are associated to q-arbs, a structure that arises from a relaxation of the capacitated prize-collecting arborescence problem in order to make it solvable in pseudo-polynomial time. Traditional inequalities over the arc formulation, like Capacity Cuts, are also used. Moreover, a novel feature is introduced in such kind of algorithms: powerful new cuts expressed over a very large set of variables are added, without increasing the complexity of the pricing subproblem or the size of the LPs that are actually solved. Computational results on benchmark instances from the OR-Library show very significant improvements over previous algorithms. Several open instances could be solved to optimality.