Research And Simulation Of Efficient Data Distribution Method For Vehicle Network Based On Traffic Situation Cognition

The Internet of Vehicles is a typical application of the Internet of Things in the field of transportation,and it has developed rapidly with the continuous advancement of intelligent transportation and smart city construction.V2X(Vehicle to Everything)technology is one of the basic technologies of the Internet of Vehicles.Vehicles will realize the coordination between vehicles,roads and networks through V2X technology to meet the state collection and traffic control needs of smart cities and intelligent transportation.At present,China has determined that 5G-V2X based on 5G technology will be used to build The Internet of Vehicles.Although 5G technology already has a large communication capacity and bandwidth,with the promotion of technologies such as driverless and edge computing,there will be more and more data communication requirements between vehicles and base stations,and networks bottleneck still exist between base stations and vehicles.The bottleneck problem requires optimization of data distribution between the base station and the vehicles to improve the performance of data distribution.Traditional methods for improving the performance of base station data distribution are mainly based on load monitoring of base stations.These methods do not consider the impact of traffic flow on base station load,and the success rate and efficiency are not high.Therefore,it is necessary to improve the efficiency and performance of base station data distribution by adjusting the data distribution load of multiple base stations.Based on the above analysis,this paper proposes an efficient data distribution method for Internet of Vehicles based on traffic situational awareness.Since the essential reason for the unbalanced load of the base station is that the traffic situation in each traffic area is not balanced,the method first models the traffic situation to realize the awareness and prediction of the traffic situation.Secondly,the method considers the influence and constraints of traffic situation on base station data distribution load balancing,and models and solves the base station data distribution equilibrium strategy based on traffic situation recognition.Specifically,the paper uses the depth residual network based on 2D weighted convolution to predict the traffic situation.The Mask-PSO algorithm and 3D convolutional neural network are used to solve the load balancing of base station data distribution.An end-to-end load-balanced deep learning model for base station data distribution based on traffic situation recognition.Finally,the paper simulates and compares the method and verifies the effectiveness of the method.