ON THE SOLUTION APPROACHES OF THE BAND COLLOCATION PROBLEM

This paper introduces the first genetic algorithm approach for solving the Band Collocation Problem (BCP) which is a combinatorial optimization problem that aims to reduce the hardware costs on fiber optic networks. This problem consists of finding an optimal permutation of rows of a given binary rectangular matrix representing a communication network so that the total cost of covering all 1's by Bands is minimum. We present computational results which indicate that we can obtain almost optimal solutions of moderately large size instances (up to 96 rows and 28 columns) of the BCP within a few seconds.