Shared bicycle dynamic redeployment method considering real-time determined information and future uncertain information

Abstract

The invention discloses a shared bicycle dynamic redeployment method giving consideration to real-time determined and future uncertain information, and the method comprises the steps: carrying out the sampling from historical data, predicting the riding order demands of shared bicycles in a certain period of time in the future, and considering the real-time distribution information of the shared bicycles, so that shared bicycle distribution information determined in real time and future uncertain shared bicycle request information can be taken into consideration, and optimizing the long-term benefits of transport vehicle path planning and shared bicycle redeployment. In order to meet the real-time requirement of the online VRBR, a mixed integer linear programming (MILP) model is adopted, and two sub-problems of transport vehicle path planning and shared bicycle re-deployment which are correlated with each other are iteratively optimized. According to the invention, the operation income of a shared bicycle operation company can be improved, and the extra cost caused by non-standard use of the shared bicycles and the labor cost required by operation and maintenance can be reduced at the same time.

Description

technical field [0001] The invention belongs to the field of information technology, and in particular relates to a dynamic re-deployment method for shared bicycles that takes both real-time determination and future uncertain information into consideration. Background technique [0002] The goal of dynamic re-deployment of shared bicycles is to hope that the number of shared bicycles at any site at any time of the day can meet the demand for riding orders. If the demand for riding orders at any time and any site is determined and known, then the traditional operational optimization algorithm can well solve the problem of dynamic redeployment of shared bicycles. However, the uncertain request information of shared bicycles in the future brings new challenges to the dynamic redeployment of shared bicycles. How to take into account the short-term benefits of real-time determined shared bicycle distribution information and the long-term benefits of future uncertain shared bicyc...

AI Technical Summary

Problems solved by technology

[0006] Existing problems: Due to the existence of prediction bias, the scheme cannot meet the dynamic distribution scenario of shared bicycles, which makes the offline shared bicycle re-deployment scheme unfeasible

However, in the real situation, at 9:00 am, the number of shared bicycles on site A is less than 5, making the offline algorithm invalid

[0009] Existing problems: due to the lack of consideration of future order demand information, it leads to frequent transfer of shared bicycles, which increases the cost of operation and maintenance

For example, at the current moment, although there are more shared bicycles on site A and fewer vehicles on site B, there is no need to transfer the shared bicycles on site A to site B, because at the next moment, the order demand on site A Much higher than the order demand on site B

Images