Scheduling method of networked vehicle system

Abstract

The invention discloses a scheduling method of a network connection vehicle system, and belongs to the field of intelligent traffic. The method specifically comprises the following steps: firstly, acquiring the number of service parties and service objects of a to-be-scheduled region and an adjacent region in real time as supply and demand information for the current moment; then, inputting supply and demand information into the trained neural network, and outputting value estimation values of all pricing factors in each region; a unique pricing factor is selected for each region by using an epsilon-greedy strategy; and finally, inputting the number of the service objects in each region and the unique pricing factor into an adjustment function, calculating the number of the service objects accepting pricing in each region, and randomly selecting the same number of service parties for service. Meanwhile, the remaining service parties which do not accept pricing in each region are input into the learned network flow scheduling model, and a scheduling strategy for each service party is output and executed; according to the method, constraints of multiple aspects such as scheduling cost, unloaded driving time, space-time pricing and supply and demand balance are considered, and revenue maximization of the service party is realized.

Description

technical field [0001] The invention belongs to the field of intelligent transportation, in particular to a scheduling method of a networked vehicle system. Background technique [0002] Vehicle wireless communication technology (Vehicle-to-Everything, V2X) is a new generation of communication technology that connects vehicles with things, where V represents the vehicle (service party), and X represents any object that interacts with the vehicle, including vehicles, people and network. V2X organically links the elements of traffic participation, which not only supports vehicles to obtain more perceptual information than bicycles, but also helps to build an intelligent networked system, which can improve traffic efficiency, save resources, reduce pollution, and reduce accident rates. As well as improving traffic management is of great significance. [0003] However, a major obstacle to the connected car system is the imbalance of supply and demand in time and space; for exa...

AI Technical Summary

Problems solved by technology

[0006] Aiming at the technical problem that the existing networked vehicle system does not jointly consider pricing and scheduling, resulting in an imbalance between the supply and demand of both parties, the present invention provides a scheduling method for the networked vehicle system, and at the same time improves the order response rate and The benefit of the service party and reduce the waiting time of the service object

Images