Highly Accurate Prediction of Radio Propagation Using Model Classifier

In this paper, we propose a measurement-based spectrum database using model classifier. In the radio propagation, path loss is the fundamental factor to recognize the coverage area. However, it is difficult to accurately estimate the radio environment only path loss estimation because of the shadowing deviation. Therefore, we estimate the propagation model including shadowing, and by determining the usage range of the estimated model, we reduce the registered data size while accurately estimating the radio environment. The database firstly accumulates the received signal strength indicator (RSSI) related to the locations of receivers and we construct the model classifier. Then, the database assigns the propagation model in each mesh so that Root Mean Squared Error (RMSE) between datasets and the models is minimized. We used measurement datasets of a 3GPP cellular band in the real environment to construct the model classifier. Our results show that the proposed method can accurately estimate the radio propagation while the registered data size is significantly reduced. Additionally, we discuss a method of power control based on the proposed method for improving the communication efficiency.