Research On Transfer Configuration Decision Of Car-sharing System Under Uncertain Conditions

With the gradual increase of the number of cars in our country,traffic congestion,environmental pollution and other problems are becoming more and more serious,affecting the quality of people’s life.Parking spaces built to meet the parking needs of vehicles occupy a lot of land resources,but still can not solve the problem of parking difficulties.However,the utilization rate of cars is not high among the people who own vehicles,and a large number of cars are idle,resulting in a waste of resources.The emergence of shared cars provides a new way to solve the above problems.The sharing of cars is characterized by the sharing of the right to use,users only enjoy the right to use,do not have ownership,so that resources have been greatly utilized.It can not only meet the needs of people for diversified travel modes,but also alleviate the urban road traffic pressure and improve traffic congestion.However,the carsharing industry in China started relatively late,and there are still many problems ramain to be solved.The problems of shortage of charging supporting facilities,insufficient network layout and difficult vehicle management still need to be optimized.In particular,due to the uncertainty of user demand,the shared vehicle inventory will bring imbalance,which will seriously affect the continuous operation of the shared vehicle system.Therefore,this study mainly focuses on the vehicle scheduling strategy of one-way station-based carsharing system.The main contents of the study are as follows:In this paper,the literature related to carsharing scheduling at home and abroad is reviewed and summarized,and the achievements and contributions of predecessors in the principle,research tools and research methods of carsharing scheduling are summarized.Secondly,this paper systematically combs the current operation mode of carsharing system in our country,and divides it into strategic layer and operation layer according to the planning level of shared vehicle system.The strategic layer focuses on the operation mode of the system and the planning of hardware facilities.The operation layer emphasizes the management of users and the mode of terminal operation.Through the above combing can have a deeper understanding of the overall design logic of the carsharing system.Thirdly,combined with the needs of users,this paper analyzes the product configuration of timeshare rental shared vehicle relative to the traditional vehicle,and introduces the related technology.At the same time,the related function configuration of the time-sharing rental and shared vehicle platform service module is analyzed,and the related technologies of vehicle scheduling configuration and user management module configuration are introduced.The whole time-sharing rental carsharing product configuration is systematically combed.Then,in order to solve the problems of uncertain user demand,unbalanced distribution of shared vehicles and lack of effective real-time scheduling,on the basis of previous studies,In this paper,a decision support model for shared vehicle scheduling under uncertainty is proposed by using opportunity constrained programming method,and a hybrid intelligent algorithm based on stochastic simulation,neural network and particle swarm optimization(PSO)is used to solve the model.Finally,the model is applied to some stations of a carsharing company in Changsha,and the effectiveness and feasibility of the vehicle scheduling configuration decision support model based on uncertainty are verified.In this paper,the application of hybrid intelligent algorithm in carsharing scheduling problem is realized,which provides a new idea for the updating and development of shared vehicle scheduling decision system in the future.