Research Of Electromagnetic Distribution Characteristics Of Mobile Base Station Co-located With High Voltage Transimission Tower Based On Ray-tracing Method

Nowadays,with the rapid development and wide application of wireless communication technology,people's life and work style are constantly changing.In the future,the number and density of base stations are large,and the cost of base station installation and operation has become an urgent problem for operators.The ‘sharing tower' which adds the function of communication base station to the existing transmission line tower is becoming a new resource sharing mode.The traditional environment around the high-voltage transmission tower has added a high-power microwave radiation source,which brings new radiation problems to the daily operation and inspection work around the transmission line tower.Therefore,the safety of operation and inspection can only be guaranteed if the electromagnetic distribution characteristics in the scene are fully understood.Most of the existing studies use the method of actual measurement or theoretical model prediction,the results of the analysis are not comprehensive enough to accurately get the electromagnetic distribution of each position in the scene.For this reason,in this paper,aiming at the scene of the base station of the common access high-voltage transmission tower,the ray tracing simulation method,which is compared with the field measurement,is applied to determine the transmission path of the signal between the receiving and transmitting antennas,calculate the electric field intensity of the receiver and train the neural network model with the simulation data to realize the prediction of the electric field intensity.Firstly,the base stations of 220 k V and 110 k V high-voltage transmission towers are modeled and simulated by ray tracing based on image method.The analysis is carried out from three areas that the inspectors often move in: the internal vertical direction of the tower,the external vertical direction of the tower and the ground horizontal direction,and the field strength distribution of each location is obtained.Compared with the measured results,it can be found that the difference between the two values is not big,and the change trend is basically the same.It can get more accurate electromagnetic distribution results,and complete the verification of the feasibility and accuracy of the method.It can also be applied to a variety of Co-located base station scenarios to complete the analysis of electromagnetic distribution characteristics efficiently and accurately.According to the simulation results,the evaluation of the electromagnetic radiation intensity of each area in the scene of the common access base station is completed.In addition,based on the simulation data,combined with the machine learning algorithm,this paper constructs and trains the prediction model based on BP(Back Propagation)neural network,RBF(Radial Basis Function)neural network and LSTM(Long Short-Term Memory)neural network respectively to realize the field strength prediction at any position in the scene.The performance is evaluated by combining error value,MSE and accuracy.Comparing the results of three kinds of neural network electric field strength prediction models,it is found that RBF neural network prediction error is relatively small,the accuracy is higher,and it fits well with the actual value,which is more suitable for the prediction of electromagnetic distribution characteristics,and also provides reference for the prediction of machine learning in the field of electromagnetic radiation.