当前位置: X-MOL 学术IEEE Wirel. Commun. Lett. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Environment Features-Based Model for Path Loss Prediction
IEEE Wireless Communications Letters ( IF 4.6 ) Pub Date : 7-20-2022 , DOI: 10.1109/lwc.2022.3192516
Yutong Sun 1 , Jianhua Zhang 1 , Yuxiang Zhang 1 , Li Yu 1 , Zhiqiang Yuan 1 , Guangyi Liu 2 , Qixing Wang 2
Affiliation  

Conventionally statistical path loss models are high-dimensional data-based without utilizing specific environment features. In this letter, a novel environment features-based model (EFBM) for path loss prediction is presented. We connect the propagation environment and channel by representing the environment with low-dimensional features: distance, deviation, volume, and blockage. The features are propagation-related, which can predict path loss directly by utilizing the Random Forest (RF) method. Compared with the data-based method, the proposed method can reduce the Root Mean Squared Error (RMSE) by 0.33 and 0.89 dB at 6 and 28 GHz and provide closer results to the Ray-Tracing (RT)-based ground-truth values.

中文翻译:


基于环境特征的路径损耗预测模型



传统的统计路径损耗模型是基于高维数据的,没有利用特定的环境特征。在这封信中,提出了一种用于路径损耗预测的新颖的基于环境特征的模型(EFBM)。我们通过用低维特征表示环境来连接传播环境和通道:距离、偏差、体积和阻塞。这些特征与传播相关,可以利用随机森林(RF)方法直接预测路径损耗。与基于数据的方法相比,所提出的方法可以在6和28 GHz处将均方根误差(RMSE)降低0.33和0.89 dB,并提供更接近基于光线追踪(RT)的地面实值的结果。
更新日期:2024-08-28
down
wechat
bug