Development of clustering algorithm for the design of telecommunication network considering cost–traffic tradeoff

In the design of telecommunication network, the network configuration using hubbing topology is useful for designing and managing the network efficiently; i.e. all of the central offices (COs) are grouped into clusters. Each cluster has one hub consisting of large-scale transmission facilities like digital cross-connect systems and ATMs. In clustering process, the community of interest and geographical factor should be considered. However, there exists a tradeoff between two factors. One is to minimize total link costs for geographical factor and the other is to maximize the total intra-cluster traffics for community of interest. Hence, this can be solved by multiobjective linear programming techniques. In this paper, the problem under consideration is formulated as two p-median subproblems taking into consideration total costs and total intra-traffics, respectively. Then we propose the algorithm to solve the problem based on the concept of cost–traffic tradeoff. The algorithm enables us to identify efficient cost–traffic tradeoff pairs. An illustration is also presented.