RFID Networks Planning Using Evolutionary Algorithms and Swarm Intelligence

In order to obtain accurate and reliable network planning in the RFID communications system, the locations of readers and the associated values for each of the reader parameters have to be determined. All these choice must optimize a set of objectives, such as coverage, economic efficiency, load balance and interference between readers. In this paper, we develop an mathematical model for planning RFID networks based on the application of two powerful optimization techniques known as Evolutionary Algorithms (EAs) and Swarm Intelligence (SI). We present a comparative study for two EAs, namely Genetic Algorithm (GA) and Evolution Strategy (ES), and one SI algorithm, namely Particle Swarm Optimization (PSO), on the RFID networks planning (RNP) problem. All the algorithms are evaluated against a test scenario (a 30 m times 30 m working space with 10 readers and 100 tags), which is subdivided into areas with different requirements. The simulation results show that the PSO algorithm obtains the superior solution for RNP problem than the other two EAs in terms of optimization accuracy and computation robustness.