基于机器学习和卫星图像的路径损耗预测

Path loss prediction based on machine learning and satellite image

基于反向传播神经网络(back propagation neural network,BPNN)构建了一种路径损耗预测模型.通过卫星图像的红、绿、蓝(red,green and blue,RGB)通道的颜色信息来表征无线通信电波传播路径的环境特征,结合路测点与基站的距离特征构建数据集,迭代训练网络参数,以预测传播路径损耗.结果表明,对跨基站路测点的预测结果与实测数据之间的相关系数达到0.83,绝对平均误差控制在0.66 dB,标准差控制在6.65 dB,说明在缺乏某一场景的详细模型和材质参数时,本文模型也能可靠预测无线通信电波的传播路径损耗.此外,本文信道模型与传统信道建模方法多方面的对比与分析表明,本文模型在相同计算资源下可以提供和传统信道建模方法相差很小的预测结果,同时大大缩短预测所需的时间,说明本文模型对传播路径损耗做出快速预测的能力可以用于无线通信网络系统的优化.

Based on back propagation neural network(BPNN),this paper establishes a channel model.The color information of red,green and blue channels(RGB)in satellite images is used to characterize the environmental characteristics of radio wave propagation path in wireless communication.We build the data set combining the color information and the distance between the measuring points and the base station and iteratively train the parameters of the net to predict the propagation path loss.The results given by the channel model show that the correlation coefficient between the predictions and the measured data reaches 0.83,absolute mean error is controlled at 0.66 dB,and standard deviation is controlled at 6.65 dB,which indicate that this model can reliably predict the propagation path loss of radio waves in wireless communication in the absence of a detailed model and material parameters of a certain scene.In the end,the model is compared with the traditional channel modeling method in many aspects.The results show that the model can provide prediction results that are slightly different from traditional channel modeling methods under the same computing resources,while greatly reducing the required time.The model can quickly predict propagation path loss in the optimization of wireless communication network system.