Roadside Cloudlet-based Resource Optimization Method In Vehicular Communication Networks

With the continuous improvement of our national economy,people's living standards have also been gradually improved.The average number of vehicles held by families is on the rise.The demand for driving experience is also getting higher and higher.This has prompted the rapid development of vehicular network communication technologies.Experiencing more high-quality applications for users is the main trend of the development of vehicular communication network in recent years.However,these emerging applications have a high demand for computing and storage capabilities of the networks.Due to the limited resources of the vehicles themselves,they have to resort to other vehicles,roadside infrastructures,or roadside cloudlets and vehicle cloudlets platforms to achieve the optimal management of resources.This paper mainly studies how to use roadside cloudlet to realize resource optimization between vehicles and roadside units.The main contents are as follows:First of all,aiming at the problem of how to balance the workload between those roadside cloudlets in the vehicular network,this paper introduces a cloudlet-based system model to capture the task response time,creates the task traffic network to get the optimal redirection flow of the tasks between the roadside cloudlets,so as to balance the task response time of the roadside cloudlets,improve the resource utilization efficiency of the network and improve the user's driving experience.The performance of this algorithm is evaluated by Matlab experimental simulation.The simulation results show that the algorithm runs fast and is easy to expand,which can match the task flow between the cloudlets,so as to significantly balance the task load of each roadside cloudlet.Secondly,after the task balance between the roadside cloudlets is reached,this paper improves the existing resource management algorithm based on fuzzy logic for the problem of resource optimization between a single roadside cloudlet and nearby vehicles---Multi-Parameter Fuzzy Logic Resource Management(MP-FLRM).The algorithm first forms a resource list that the vehicle requests to the roadside cloudlet and uses the V2 I communication mode to collect the queuing waiting time for each resource(computing resource and storage resource)of the vehicle in the network,downloading time and uploading time,and transform each time to a time set.Based on the fuzzy logic theory,more time parameters are considered in the network when the vehicle requests resources,which modulates the survival time of the resources in the server of roadside cloudlet so as to optimize the resources of the system and improve the resource utilization efficiency of the vehicle.By using Matlab experimental simulation to compare system throughput with different arrival rates,different time and different amount of storage resources,the results show that MP-FLRM can effectively improve system throughput and improve system performance.