Channel Gain Map Construction based on Subregional Learning and Prediction

TL;DR

This paper introduces a subregional learning approach for constructing channel gain maps in 6G wireless systems, dividing the environment into subregions to improve prediction accuracy with finite data.

Contribution

It proposes a novel subregional learning scheme with data-driven clustering and boundary data reuse to enhance channel gain map prediction in complex environments.

Findings

Effective in complex propagation environments

Improves prediction accuracy with subregional models

Validated through simulation results

Abstract

The construction of channel gain map (CGM) is essential for realizing environment-aware wireless communications expected in 6G, for which a fundamental problem is how to predict the channel gains at unknown locations effectively by a finite number of measurements. As using a single prediction model is not effective in complex propagation environments, we propose a subregional learning-based CGM construction scheme, with which the entire map is divided into subregions via data-driven clustering, then individual models are constructed and trained for every subregion. In this way, specific propagation feature in each subregion can be better extracted with finite training data. Moreover, we propose to further improve prediction accuracy by uneven subregion sampling, as well as training data reuse around the subregion boundaries. Simulation results validate the effectiveness of the proposed scheme in CGM construction.