A Novel Machine Learning Scheme for mmWave Path Loss Modeling for 5G Communications in Dense Urban Scenarios

Abstract

Accurate and efficient path loss prediction in mmWave communication plays an important role in large-scale deployment of the mmWave-based 5G mobile communication systems. Existing methods often present limitations in accuracy and efficiency and fail to fulfill the requirements of cell planning, especially in dense urban environments. In this paper, we propose a novel training method called multi-way local attentive learning, which allows for learning from multiple perspectives on the same set of training samples with local attention paid to each subset of the entire dataset. The sample data set can be partitioned in various ways with respect to different attributes, such that a larger amount of knowledge can be extracted from the same data set. The proposed scheme outperforms the existing schemes in terms of prediction accuracy at the average RMSE of 6.01 dBm.

Predicting Path Loss of an Indoor Environment Using Artificial Intelligence in the 28-GHz Band

“…Different filters are used to convolve the inputs and provide several output activation maps. This is achieved by multiplying the neurons of the input activation maps with the weight of the filter, thereby connecting the output and input of the activation maps [10,11].…”

“…To simplify the equation, the value of the bias variable of Equation ( 11) is initialized to zero. Once the loss is obtained in (10), the parameter is fed back to the neural networks to initiate a new calculation and reduce the error. Following a few iterations, the parameter values become stable to create a path loss model.…”