Optimization of Dielectric Resonator Antenna based on Machine Learning and PSO Methods

With the rapid growth of the communication technologies, the communication systems put higher requirements for the performance of antennas such as bandwidth and gain. To meet the higher demands, lots of researchers investigate the optimization problem of antennas. In this paper, we propose a dielectric resonator antenna optimization scheme based on machine learning and particle swarm optimization (PSO). We first adopt PSO to optimize the parameters of machine learning and then find the mapping relationship between the antenna model parameters and their responses by machine learning. Finally, we obtain the antenna model parameters according to the inverse mapping of the target response. Simulation results show that our proposed scheme is feasible and obtains superior performance compared with the existing schemes.