Channel Gain Map Construction based on Subregional Learning and Prediction
This work addresses the challenge of environment-aware wireless communications for 6G, but it appears incremental as it builds on existing prediction methods by adding subregional modeling.
The paper tackles the problem of predicting channel gains at unknown locations for 6G wireless communications by proposing a subregional learning-based scheme that divides the map into data-driven clusters and trains individual models per subregion, with simulation results validating its effectiveness.
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.