Resarch On Efficeient And Reliable C-V2X Communication Mechanism For Platoon

Platooning is considered one of the representative 5G use cases.However,due to the small distance between the front and rear vehicles in the platoon,the platoon needs more reliable wireless communication,to improve the fuel and driving efficiency of vehicles on the premise of ensuring the safety of vehicles.However,due to the characteristics of the open wireless channel,the confidentiality and reliability of communication are always two inherent challenges for efficient and reliable communication of platoon.Hostile jamming will reduce the success rate of platoon communication,which will cause security risks for the connected platoon.At the same time,the information sent by the platoon often involves the privacy of the members of the platoon.If it is obtained and cracked by malicious eavesdroppers,it may cause irreparable consequences to the platoon members.Given the above problems,this thesis first introduces the related technologies and algorithms of hostile interference.Aiming at the scenarios where the hostile interference strategy of attackers is unknown,a resource selection algorithm based on reinforcement learning is proposed.Since the resource selection action of the platoon includes discrete channels and continuous transmission power at the same time,it is a mixed action space.In order to improve the performance of the algorithm,this thesis proposes a resource selection algorithm combining Dueling DQN and deep deterministic policy gradient networks,and introduces policy fingerprints to solve the problem of environmental instability when two networks coexist.Finally,simulation experiments verify the effectiveness of the proposed algorithm.Furthermore,to explore how to use the distributed resource allocation scheme to meet the requirements of high reliability and low delay of information transmission for each legitimate platoon in the system under the time-frequency resource-constrained scenario,this thesis considers a multi-platoon distributed resource allocation scenario.Efficient resource allocation between platoons has been a challenge,especially considering that the channel and power selected by each platoon will affect other platoons.Therefore,platoons need to coordinate with each other to ensure the groupcast quality of each platoon.To solve these challenges,a distributed resource allocation algorithm based on Value-Decomposition Networks is proposed.Our scheme utilizes the historical data of each platoon for centralized training.During distributed execution,the platoon only needs their local observations to make decisions.At the same time,the training burden is decreased by sharing the neural network parameters between platoons.Simulation results show that the proposed algorithm has excellent convergence.Compared with the other algorithms,our proposed solution can effectively reduce the probability of platoon groupcast failure and improve the quality of platoon groupcast.