Efficient k-means based clustering scheme for mobile networks cell sites management

Abstract

Telecommunication network infrastructures in Africa and the Middle East regions, are deployed and operated in challenging environments that are highly scattered particularly in rural areas. Moreover, considerable number of cell sites are located in areas difficult to access. Furthermore, low income in rural areas does not allow a fast return on investment since the cost of deployment and operation of a cell site is considerable. These issues lead to a difficult human resource management, particularly, in the assignment of technicians to cell site for maintenance purpose. In this paper, an optimized scheme for costs of maintenance operations on cell sites is proposed. We used the k-means clustering algorithm for allocating field technician to a pool of cell sites. Moreover, to alleviate the k-means sensitivity to initialization, we proposed an initialization method that is based on the geometry of a sphere. We conducted series of experiments with sample of thousands of cell towers from OpenCellID and the results demonstrate the effectiveness of the proposal.