High-speed rail network coverage prediction method and device based on machine learning and ray tracing

Abstract

The embodiment of the invention relates to a high-speed rail network coverage prediction method and device based on machine learning and ray tracing. The method comprises the steps that a three-dimensional electronic map of a target high-speed rail scene is acquired; based on the three-dimensional electronic map of the target high-speed rail scene, ray tracking simulation is used to calculate a preliminary prediction value of each position measurement point in the target high-speed rail scene; the preliminary prediction value is corrected through machine learning based on the actual measurement value of each position measurement point in the same target high-speed rail scene in combination with the preliminary prediction value of each position measurement point to obtain a correction factor of the preliminary prediction value; and according to the correction factor of the preliminary prediction value, high-speed rail scene receiving field intensity prediction is carried out by using ray tracking simulation. In the embodiment of the invention, a ray tracking simulation technology and deep reinforcement machine learning are utilized to provide a more accurate input basis for scene correction, the application deployment range is more universal, and the robustness is higher.

Description

technical field [0001] Embodiments of the present invention relate to the field of wireless technology, and in particular to a method and device for predicting coverage of a high-speed rail network based on machine learning and ray tracing. Background technique [0002] With the rapid development of wireless technology, the complexity of radio wave propagation has brought great challenges to the deployment and optimization of base stations in high-speed rail GSM-R wireless networks. Therefore, effectively predicting base station coverage is the basis for wireless network base station deployment planning and optimization. It is also the premise of accurately locating existing problems in the existing network. It can improve the efficiency of base station site selection, ensure communication, and reduce the cost of deployment trial and error. Key points and difficulties of wireless network planning and optimization. [0003] Existing network optimization relies on repeated te...

AI Technical Summary

Problems solved by technology

[0003] Existing network optimization relies on repeated testing of low-speed vehicles and manual debugging, which has problems such as low efficiency, long time, high cost, and difficulty in popularization. It is urgent to use machine learning and ray tracin

Images