Research on Coverage Ability Assessment of High and Low Frequency based on Machine Learning

Abstract

With the rapid construction of 5G network in China, how to guide reasonable network planning and construction through accurate network coverage ability assessment, and build a 5G high-low-frequency hybrid network with low cost and high efficiency, has become an important topic urgently needed to be studied by telecommunication suppliers. Firstly, the propagation models applicable to 2.1G and 3.5G are studied and theoretically calculated. Next, reasonable suggestions are put forward for the problems existed in the calibration for traditional Propagation Model, and the accuracy of the propagation model is improved by adopting the machine learning algorithm and model. Finally, based on outfield test results, the propagation model calibrations for 3.5G and 2.1G bands are conducted, and reasonable suggestions are put forward for 5G high and low frequency hybrid networking scheme.