发表机构
Fraunhofer FKIE; Hochschule Bonn-Rhein-Sieg（弗劳恩霍夫FKIE研究所; 波恩-莱茵-锡格应用科学大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对LPWAN的路径损耗预测，采用结合LiDAR地形特征的随机森林与坐标数据的k近邻，发现两种机器学习模型在不同训练规模下均优于基线模型，且留一网关验证显示随机森林迁移性能更优。
AI 中文摘要
像LoRa这样的低功耗广域网（LPWAN）正越来越多地部署于智慧城市应用中，这需要准确的路径损耗预测以实现有效的网络规划。传统的经验传播模型在这些场景中往往精度有限。我们研究用于LoRa路径损耗预测的机器学习模型，利用城市部署的真实测量数据，系统分析预测精度如何随训练集规模变化。我们的方法采用结合LiDAR衍生地形特征的随机森林（Random Forest），以及结合坐标数据的k近邻（k-Nearest Neighbors），将它们的性能与已建立的经验模型和专用LPWAN模型进行比较。在随机池化划分下，两种机器学习模型在所有评估的训练集规模上均持续优于所考虑的基线模型。在最大训练规模下，它们的均方根误差（RMSE）低于6.5 dB，而最佳基线模型的RMSE为9.7 dB，表明在部署内插值预测准确。留一网关验证对该结果进行了验证：随机森林（RF）对未见过的网关表现出依赖位置的迁移性能，部分网关的精度有适度下降，而其他网关则出现更大误差；仅用坐标数据的k近邻在网关位置未见过时，精度大幅下降。
英文摘要
Low Power Wide Area Networks like LoRa are increasingly deployed for smart city applications, requiring accurate path loss prediction for effective network planning. Traditional (empirical) propagation models often exhibit limited accuracy in these scenarios. We investigate machine learning models for LoRa path loss prediction, systematically analyzing how prediction accuracy scales with training set size using real-world measurements from an urban deployment. Our approach employs a Random Forest with LiDAR-derived terrain features and k-Nearest Neighbors with coordinate data, comparing their performance against established empirical models and specialized LPWAN models. Under random pooled splits, both ML models consistently outperform the considered baseline models across the evaluated training-set sizes. At maximum training size, they achieve RMSE values below 6.5 dB compared to 9.7 dB for the best baseline, indicating accurate within-deployment interpolation. A leave-one-gateway-out check qualifies this result: RF shows placement-dependent transfer to held-out gateways, with moderate degradation for several gateways but larger errors for others, whereas coordinate-only k-NN degrades substantially when the gateway location is unseen
CommentsAccepted at IEEE Conference on Local Computer Networks (LCN)
