CNN-Based mmWave Path Loss Modeling for Fixed Wireless Access in Suburban Scenarios

Abstract

Path loss modeling of millimeter waves is regarded as one of the most challenging problems in the design of the fifth-generation (5G) mobile communication networks due to the high susceptibility to various environmental influences. We present a novel convolutional neural network (CNN)-based path loss modeling method based on a set of 28 GHz mmWave field measurements in suburban scenarios. Enhanced local area multi-scanning (E-LAMS) algorithm that provides a CNN with path loss environmental information is proposed. A new CNN structure with four subnetworks and feature-sharing layers added between convolutional layers is also proposed. The proposed methods demonstrate their superior performance over empirical models and deterministic models in terms of accuracy and complexity. The root-mean-square error of 8.59 dB has been achieved in path loss prediction in the test scenarios.