Lagrangean based methods for solving large-scale cellular network design problems

  • Authors:
  • Filipe F. Mazzini;Geraldo R. Mateus;James Macgregor Smith

  • Affiliations:
  • Departamento de Ciência da Computação, Universidade Federal de Minas Gerais, Caixa Postal 702, CEP 30.123-970 Belo Horizonte, Minas Gerais, Brazil;Departamento de Ciência da Computação, Universidade Federal de Minas Gerais, Caixa Postal 702, CEP 30.123-970 Belo Horizonte, Minas Gerais, Brazil;Department of Mechanical and Industrial Engineering, 114 Marston Hall, University of Massachusetts Amherst, Amherst, MA

  • Venue:
  • Wireless Networks
  • Year:
  • 2003

Quantified Score

Hi-index 0.00

Visualization

Abstract

The cellular network design (CND) problem is formulated as a comprehensive linear mixed integer programming model integrating the base station location (BSL) problem, the frequency channel assignment (FCA) problem and the topological network design (TND) problem. A solution algorithm based on Lagrangean relaxation is proposed for solving this complex cellular network design problem. Pursuing the optimum solution through exact algorithms to this problem appears to be unrealistic considering the large scale nature and NP-hardness of the problem. Therefore, the solution algorithm strategy consists in computing effective lower and upper bounds for the problem. Lower bounds are evaluated through a Lagrangean relaxation technique and subgradient method. A Lagrangean heuristic is developed to compute upper bounds based on the Lagrangean solution. The bounds are improved through a customized branch and bound algorithm which takes in account specific knowledge of the problem to improve its efficiency. Thirty two random test instances are solved using the proposed algorithm and the CPLEX optimization package. The results show that the duality gap is excessive, so it cannot guarantee the quality of the solution. However, the proposed algorithm provides optimal or near optimal solutions for the problem instances for which CPLEX also provides the optimal solution. It further suggests that the proposed algorithm provides optimal or near optimal solutions for the other instances too. Finally, the results demonstrate that the proposed algorithm is superior to CPLEX as a solution approach for the CND problem.