| The Internet of Vehicles(Io Vs)is a distributed network that supports the real-time communication of various entities in the transportation field.It can bring huge economic benefits and has attracted the attention of governments and enterprises in various countries.The push of service information such as parking spaces and charging piles is a typical representative of non-safety-related applications in the Io Vs.It is very important to users and has a very wide range of application scenarios.It is of great significance to study such non-safety-related applications.The non-safety-related applications provided by service providers to users are mostly related to destinations of the users,but users will not actively report their traveling destinations.Therefore,it is necessary to predict the user’s traveling destination information in real-time to provide services and benefit from it.After the service providers send the destination-related information to vehicles through the roadside unit,the vehicle will forward it to other vehicles by vehicle-to-vehicle communication,which will also generate corresponding revenue for service providers.Therefore,the strategy of sending information to users should comprehensively consider the destination information of the driving vehicles and the changing law of the neighboring nodes of the vehicles,so as to maximize the revenue obtained by service providers after sending the destination-related information.For this reason,the main research contents of this article are as follows:(1)Aiming at the problem that users will not actively report destination information,this paper proposes a real-time destination prediction algorithm.The algorithm first divides and represents the complete trajectory of the vehicle,and then proposes the use of the divided sub-trajectory.Based on the clustering results,a deep learning-based destination prediction algorithm is proposed.Simulation experiments and comparison results on public data set show that the destination prediction algorithm proposed in this paper can achieve better results.(2)Aiming at the strategy of sending information to users,this paper proposes an information delivery mechanism based on trajectory prediction.In order to deliver destination-related information to users,the mechanism ensures the accuracy of information delivery based on proposed destination prediction algorithm,for bringing benefits to service providers.Considering that the vehicles will forward the information to other vehicles after receiving the information from the roadside unit,this process will also bring benefits to the service provider.For the purpose of maximizing the benefits of service providers,based on destination prediction and the number of neighbor nodes,an information transmission mechanism based on trajectory prediction is proposed.This paper evaluates its performance,and the simulation results show the effectiveness of the information delivery mechanism. |
