Research On Taxi Sharing In Urban Road Network Based On Intelligent Non-cooperative Game Theory

As the number of urban population grows and the demand for transportation increases,a large number of private cars have appeared in the urban road network,which not only leads to traffic congestion,but also energy consumption exacerbates environmental pollution as well as waste of resources.Especially during peak travel periods,people face difficulties in getting a cab and traffic congestion,and cab sharing is a promising way to save resource consumption and ease traffic congestion while meeting people’s commuting needs.Passengers with similar routes traveling together in a single cab can maximize the use of the vehicle’s resources while reducing costs for drivers and passengers.Currently,most of the existing cab sharing methods are based on intelligent algorithms and have achieved certain research results,however,there are still shortcomings in the existing research.First,most of the taxi sharing models are only studies of the vehicle dispatching methods involved,focusing only on how to efficiently dispatch satisfactory vehicles for passengers and ignoring the impact of driving paths on travel efficiency.Second,most of the cab sharing studies guide single vehicles to follow the optimal route recommended by the system,ignoring the influence between vehicles,which leads to a large amount of traffic flow into a route and causes congestion on that route.Finally,the existing vehicle scheduling algorithm research faces the challenge of large computational volume.To address the above problems,the research work in this paper is as follows:(1)For taxi sharing research,this paper establishes a non-cooperative game-based taxi sharing model for urban road networks,in which each element of passenger requests and taxi states are described,and a non-cooperative game is introduced to establish the taxi sharing model considering the influence of decision making and resource competition among vehicle drivers.And constraints such as time constraint,number of passengers constraint,and detour rate are proposed,and the benefit function calculation method of the driver game is given.Based on the constraints,the overall formulation of the taxi sharing model is presented.(2)For the vehicle scheduling problem,the Candidate Vehicle Scheduling based on Constraints(CVSC)algorithm is proposed in this paper.In order to solve the problem of large computation of vehicle scheduling algorithm,the urban road network is gridded.At the same time,suitable candidate vehicles are scheduled for passengers through the screening of time constraints,grid areas,and road network distances.Finally,the shared arrangement is determined by passenger’s request insertion check.(3)For the driver’s route decision problem,this paper designs an intelligent non-cooperative game algorithm to solve the driver’s Nash equilibrium strategy,matching the appropriate vehicle from the candidate vehicles and providing an optimized route for passengers,improving the overall benefits of all taxi drivers and reducing costs.(4)In order to evaluate the feasibility of the whole taxi sharing model framework in this paper,experiments are carried out on real road network and artificial road network.By comparing the taxi sharing model built in this paper with three common car-sharing frameworks,the experimental results show that the feasibility and effectiveness of the taxi sharing model proposed in this paper can not only alleviate certain traffic congestion,but also reduce the cost of transportation,improve the utilization of resources and reduce energy consumption.