Hierarchical provisioning for cellular networks

We propose a hierarchical provisioning methodology to balance the network load within each location and routing area, as well as minimize the location and routing area update signaling cost. The hierarchical provisioning methodology consists of four optimization planes for cellular coverage area: 1) cell-oriented intra-SGSN layer, which is optimized routing areas covering the intra-SGSN signaling cost, paging cost, and routing area load balancing; 2) routing area-oriented intra-mobile switching center (MSC) layer, which is optimized location areas covering the intra-MSC signaling cost and location area load balancing; 3) routing area-oriented inter-SGSN layer, which is optimized SGSN coverage areas covering the inter-SGSN signaling cost, RNC, and SGSN load balancing; and 4) location area-oriented inter-MSC layer, which is optimized MSC coverage areas covering the inter-MSC signaling cost and MSC load balancing. We apply the niched Pareto genetic algorithm (GA) to the provisoning problem, which optimizes multiple objectives by incorporating the concept of Pareto domination in its selection operator, and applying a niching pressure to spread its population out along the Pareto optimal tradeoff surface. We then propose a schema-based partially matching crossover using a tournament size, where the crossover pairs are chosen in two steps, first based on the class ranking and then schema ranking. The new offspring are modified using the RA-based for intra- and inter-SGSN layers.