Supply and demand prediction and scheduling method and device for shared electric vehicle

Abstract

The invention provides a supply and demand prediction and scheduling method and device for a shared electric vehicle, and the method comprises the steps: inputting a historical target sequence, a static covariable sequence and a historical covariable sequence of all to-be-predicted network points, and a future covariable sequence of each to-be-predicted network point constructed based on the current moment into a demand prediction model, and obtaining a future time sequence of each to-be-predicted network point; processing the future time sequence of each to-be-predicted network point to obtain a prediction result of the to-be-predicted network point; according to each prediction result, determining whether the network point corresponding to each prediction result needs to perform vehicle scheduling; if at least one predicted website needs to be scheduled, generating a scheduling instruction of the vehicles between the corresponding websites by taking at least one of the shortest total time, the shortest total distance and the maximum total order quantity as an optimization target; reasonably configuring limited vehicle resources and network parking space resources, and reducing the overall scheduling cost, and finally, achieving the purposes of reducing cost and increasing efficiency.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence, and more specifically, relates to a method and device for supply and demand forecasting and dispatching of shared electric vehicles. Background technique [0002] With the large-scale development of shared bicycles, the concept of shared economy has spread rapidly, and shared cars have also entered the market and entered people's lives. In the current time-sharing rental car sharing business model, the operating vehicles are generally new energy electric vehicles. The operator has set up a large number of outlets in the city. The outlets have specific parking spaces for parking or charging. Users need to pick up the car at these specific outlets. Or return the car. However, due to the limited vehicle resources and outlet parking space resources, in order to rationally allocate these resources, the outlets have available vehicles when the user needs a car, and the outlet has vacan...

AI Technical Summary

Problems solved by technology

[0003] At present, the dispatching of vehicles by shared car companies mainly focuses on solving two problems: one is that the number of vehicles returned by some outlets exceeds the number of parking spaces set by the outlets, resulting in an explosion point. Dispatchers generally dispatch vehicles to nearby vacant parking spaces. The second is the long-term unmanned rental of vehicles waiting to be transported in some outlets. The dispatchers mainly dispatch the vehicles to nearby outlets that may generate orders based on experience.

Due to the inaccurate judgment of dispatchers on the future supply and demand of outlets, there are a large number of invalid dispatches in manual dispatching, and there are also problems with unreasonable dispatching routes, which cost a lot of money

Images