UnetRay: A Prediction Method of Indoor Radio Signal Strength Distribution

Efficient and accurate indoor radio signal strength prediction methods are essential for the design and operation of wireless communication systems. Recently, attempts have been made to combine radio propagation prediction with deep learning. Inspired by recent advances in computer vision, we propose a prediction model using a convolutional encoder-decoder structure fused with Swin Transformer module. Specifically, we embed the Swin Transformer into the U-Net structure to enhance the global modeling capability of the U-Net network, which can be trained to predict the strength of signals received in a given indoor environment. More importantly, once trained for a sufficient number of scenarios, the model can directly predict the signal strength in unknown indoor environments. The simulation results verify that the model is more effective than the traditional U-Net, with a reduction in validation error of about 40%.

I. Introduction

Reference Signal Received Power (RSRP) indicates the signal strength of the base station at a certain location of the user equipment. A larger RSRP value indicates a stronger ability to receive the signal and better signal quality. Therefore, accurate prediction of RSRP can improve the reliability and stability of 5G networks and optimize network coverage and performance. As wireless communications have achieved significant growth, the prediction of wireless communication propagation characteristics in indoor environments has become more important, and the ability to determine the optimal base station location and predict its coverage without the need for a series of very expensive and time-consuming measurements has become even more relevant. Therefore, it is crucial to develop effective propagation models for indoor wireless communications to provide accurate guidance for the design of wireless systems. However, indoor radio signal strength prediction is a challenging problem. It involves many factors, including the structure of the building, materials, location of equipment, and performance of antennas. Due to the complexity and interplay of these factors, accurate prediction of indoor radio signal strength is a challenging task.