Transformer-Based Neural Surrogate for Link-Level Path Loss Prediction from Variable-Sized Maps
This work addresses network planning and handover problems for wireless communication systems, presenting an incremental improvement in method for map-based path loss prediction.
The paper tackled predicting link-level path loss from variable-sized maps using a transformer-based neural network, achieving efficient learning from sparse data and good generalization to new maps.
Estimating path loss for a transmitter-receiver location is key to many use-cases including network planning and handover. Machine learning has become a popular tool to predict wireless channel properties based on map data. In this work, we present a transformer-based neural network architecture that enables predicting link-level properties from maps of various dimensions and from sparse measurements. The map contains information about buildings and foliage. The transformer model attends to the regions that are relevant for path loss prediction and, therefore, scales efficiently to maps of different size. Further, our approach works with continuous transmitter and receiver coordinates without relying on discretization. In experiments, we show that the proposed model is able to efficiently learn dominant path losses from sparse training data and generalizes well when tested on novel maps.