Public service system design by radial formulation with dividing points

In this paper, we introduce an approximate approach to public service system design making use of a universal IP-solver. The solved problem consists in minimization of the total discomfort of system users, which is usually proportional to the sum of demand-weighted distances between users and the nearest source of provided service. Presented approach is based on radial formulation. The disutility values are estimated by some upper and lower bounds given by so-called dividing points. Deployment of dividing points influences the solution accuracy. The process of the dividing point deployment is based on the idea that some disutility values can be considered relevant and are expected to obtain in the optimal solution. Hereby, we study various approaches to the relevance with their impact on the accuracy and computational time.