Evolutionary algorithm for cost reduction in cellular network

Abstract

Mobility management is a prime issue in a wireless computing environment. There is a need to develop various algorithms that could capture this complexity and used to solve the mobility management scenarios. When a mobile user moves from one cell to another cell some amount of cost is acquired for the same. These cells are assigned as either “reporting cell” or “non-reporting cell”, also known as reporting cell planning problem (RCP). In this paper, to reduce the total cost, two optimization techniques are adopted and compared to solve the problem. Total cost in location management signifies location update cost and paging cost. Two optimization algorithms needed to capture the issue are Genetic Algorithm (GA) and Binary Particle Swarm Optimization Algorithm (BPSO) which is also compared to measure the performance in terms of cost. For the same problem BPSO is shown to outperform GA in terms of quality of solution and also proved to be efficient in a competitive approach for the several benchmark issues. The simulation results also indicate BPSO is robust, gives higher solution quality and offers faster global convergence. These proposed techniques are also validated on service data and compared with the synthetic data of the different subscribers present in different reporting cells. A number of optimization problems are solved using this evolutionary algorithm and results obtained are quite satisfactory.