Propagation Path Loss Estimation Using Nonlinear Multi-regression Approach

Some theoretical and experimental models have been considered for the prediction of the path loss in mobile communication systems. This paper presents an alternative method to model the path loss characteristics, taking into account data analytical methods to discover dependency pattern among propagation model parameters. We applied the concept of nonlinear multi-regression to predict path losses from the collected data, such as considering carrier frequency, path loss exponent, and distance between transmitter and receiver. Based on this information, the pseudo gradient search approach is adopted to determine the optimal search direction, build propagation knowledge, and accurately estimate the path loss. Finally, the free space path loss is adopted in order to validate our approach. The results are found to be well in agreement with theoretical results.