Effective outdoor pathloss prediction: A multi-layer segmentation approach with weighting map

TL;DR

This paper presents a ResNet-based deep learning model with a novel weighting map technique for improved outdoor pathloss prediction, outperforming existing models in accuracy and computational efficiency.

Contribution

The study introduces a multi-layer segmentation approach with a weighting map to enhance pathloss prediction accuracy and reduce computational complexity.

Findings

Outperforms PPNet, RPNet, and ViT by 1.2-3.0 dB in prediction accuracy.

Reduces FLOPs by 60% compared to benchmark models.

Ablation studies show the weighting map significantly improves performance.

Abstract

Predicting pathloss by considering the physical environment is crucial for effective wireless network planning. Traditional methods, such as ray tracing and model-based approaches, often face challenges due to high computational complexity and discrepancies between models and real-world environments. In contrast, deep learning has emerged as a promising alternative, offering accurate path loss predictions with reduced computational complexity. In our research, we introduce a ResNet-based model designed to enhance path loss prediction. We employ innovative techniques to capture key features of the environment by generating transmission (Tx) and reception (Rx) depth maps, as well as a distance map from the geographic data. Recognizing the significant attenuation caused by signal reflection and diffraction, particularly at high frequencies, we have developed a weighting map that emphasizes the areas adjacent to the direct path between Tx and Rx for path loss prediction. {Extensive simulations demonstrate that our model outperforms PPNet, RPNet, and Vision Transformer (ViT) by 1.2-3.0 dB using dataset of ITU challenge 2024 and ICASSP 2023. In addition, the floating point operations (FLOPs) of the proposed model is 60\% less than those of benchmarks.} Additionally, ablation studies confirm that the inclusion of the weighting map significantly enhances prediction performance.