Optimization Design Based On UAV-assisted Communication Network Deployment In Internet Of Vehicles

With the development of the economy,the number of vehicles is rising.As an important part of intelligent transportation,Internet of Vehicles technology has been continuously valued by academia and industry.However,in some special scenarios,such as traffic hotspots and disaster areas,vehicles cannot receive reliable communication services.At this time,unmanned aerial vehicle(UAV)was introduced as an emergency auxiliary communication method.As a mobile base station,UAV has the advantages of fast deployment,strong flexibility and low cost.Therefore,UAVs have good application prospects in some specific scenarios,such as emergency communication support.However,UAV-assisted Internet of Vehicles communication also faces many difficulties and challenges,first of all,the Internet of Vehicles has the problem of rapid network topology changes and cannot maintain stable communication connections between vehicles.Secondly,due to the limited energy of UAVs,the deployment of UAVs is also an issue that needs attention.This thesis aims at the network deployment problem in the Internet of Vehicles,designs suitable models according to various practical application scenarios,and gives appropriate solutions.The main work of this thesis is as follows:(1)For the problem of unstable communication between vehicles caused by high-speed movement of vehicles in the Internet of Vehicles,this thesis proposes a clustering algorithm based on reliable node screening,which filters the neighbor nodes of each vehicle according to the vehicle direction and vehicle communication link survival time,forms a reliable node list through the filtered nodes,and then calculates the weight based on the three indicators of reliable node degree,relative speed and relative distance,and then selects the cluster head.Simulation results show that the proposed algorithm has good cluster stability.(2)For the scenario of multi-UAV providing communication services for vehicles,the positions of UAVs and user association strategies are optimized to minimize the emission power of UAVs while meeting the minimum information rate of vehicle users.The optimization problem is divided into two problems: user association strategy and UAVs’ position optimization.The user association strategy uses the clustering algorithm based on reliable node screening to self-organize the vehicles in advance,and each cluster has a unique UAV to provide communication services.The position optimization problem of UAVs has multiple constraints,and an improved particle swarm algorithm is proposed to solve this problem.Simulation results show that the proposed algorithm can effectively reduce the emission power of UAVs.(3)In view of the natural disaster scenario,the ground communication facilities are seriously damaged,and the UAV faces problems such as limited energy and inability to obtain ground vehicle location information in real time,this thesis proposes a multi-agent Q-learning algorithm based on decentralization.The algorithm makes autonomous decisions through local observations of UAVs and connectivity information broadcast by neighboring UAVs.Each UAV is equipped with an independent agent that learns the UAV’s trajectory while jointly optimizing the UAV’s energy consumption and the number of connected vehicles.Simulation shows that the algorithm proposed in this paper has advantages in energy consumption and number of connected vehicles.