The Architecture And Perf Ormance Optimization Of Cloud And Fog Based Software Defined Internet Of Vehicles

As one of the core technologies of the internet of things and smart city,internet of vehicles(IOV)has been rapidly developed in recent years.Various communication protocols and network services have been widely developed and applied to the IOV.They can provide a variety of information services and comfortable driving environment for users and also play a great role in improving urban traffic conditions.However,with the increasing amount of vehicles and types of applications,some bottlenecks have appeared such as high heterogeneity,poor mobility support and lack of extensibility.At the same time,the emergence of new technologies and architectures can provide an opportunity to improve these problems.So how to develop the new generation of IOV has become one of the most important research topics.This paper firstly introduces the structure,technologies and problems of the traditional internet of vehicles,and then focuses on the analysis of the new scheme of cloud and fog based software defined internet of vehicles.On the basis of the proposed new architecture,this paper concentrates on the performance optimization.The main work of this paper is stated as follows:(1)A new architecture naming cloud and fog based software defined internet of vehicles(CFSD-IOV)is proposed.Aiming at the problems of traditional internet of vehicles,a detailed comparison of several popular alternative technologies is presented.The architecture is divided into four layers,which comprehensively utilizes the advantages of cloud computing,fog computing and software defined network.It can provide flexibility,scalability and mobile support which didn't exist in traditional ways.Then this paper introduces the components and potential applications of each layer and provides the theoretical basis for the following performance optimization.(2)This paper puts forward the cooperative cloud computing and fog computing model and designs a new resource management program.Different from working independently,in this paper,the core fog servers can forward the workload to each other and offload it from the cloud server together by the establishment of the cooperative fog servers on the bottom layer.Then by the controller and virtualization technology,the quality of service and energy consumption are optimized respectively from the system level and the device level.And to solve the optimization problem,this paper proposes an algorithm naming double side constrained particle swarm.Finally,by the experimental simulation,the advantages of the algorithm are verified,and the communication delay and energy consumption are also improved by the resource management program.(3)A service preloading scheme based on trajectory prediction and an improved trajectory prediction algorithm are proposed.In order to reduce the delay caused by the application of software defined network to the internet of vehicles,a new service preloading scheme is proposed.Through trajectory prediction,it can relieve the problem of the extra overhead in the traditional scheme.Then the improved confidence level probability suffix tree algorithm is designed,which can improve the effectiveness of the scheme by training the historical trajectory and making the real-time prediction.Experimental results show that the service preloading scheme in this paper is proved to reduce the delay of real-time communication and improve the quality of service without affecting the performance of the switches.And compared with the traditional algorithms,the proposed algorithm improves the accuracy and complexity.At the end of the paper,the research results are summarized,and the future research directions are also discussed.