Public bicycle dynamic scheduling method based on site short-term demand prediction

Abstract

The invention discloses a public bicycle dynamic scheduling method based on site short-term demand prediction. The method comprises the steps of collecting a site free pile number time sequence, constructing a neural network model to predict the short-term demand of each site, calculating the scheduling time window and demand on the basis, constructing a dynamic scheduling model minimizing the cost of scheduling and maximizing satisfaction, solving a scheduling scheme, and adjusting the scheduling plan through information updating. By combining site short-term demand prediction and dynamic scheduling, the efficiency and accuracy of public bicycle scheduling are ensured, the service level of public bicycles is improved, and public bicycles are made more attractive.

Description

technical field [0001] The invention belongs to the field of intelligent dispatching of public bicycles, and relates to a dynamic dispatching method of public bicycles based on short-term demand prediction of stations. Background technique [0002] With the acceleration of the urbanization process, the travel needs of residents have become more diversified, which has promoted the rapid development of motorization. However, the rapid increase in the number of motor vehicles has brought about a series of problems such as urban traffic congestion, noise, and environmental pollution, which have restricted sustainable development of cities. In order to solve the problem of urban transportation, it has become a broad consensus of the whole society to give priority to the development of urban public transportation. The whole transportation service, public bicycle therefore arises at the historic moment. [0003] "Public bicycle" refers to a means of transportation in which the go...

AI Technical Summary

Problems solved by technology

In reality, the way of dispatching through manual inspection is outdated in technical means, insufficient in accuracy, and low in efficiency, and it is difficult to meet the dispatching needs of peak periods

The traditional scheduling method lacks real-time prediction of the demand for public bicycles at the site, and is mostly based on the site demand before dispatching. It does not consider the mobility of public bicycles and the dynamics of site demand changes. During the scheduling process, it is often impossible to schedule the site in time, and Insufficient scheduling accuracy, leading to low service levels of public bikes

Images