Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Shared bicycle scheduling method based on deep reinforcement learning

A technology of reinforcement learning and scheduling methods, applied in the direction of neural learning methods, constraint-based CAD, design optimization/simulation, etc., can solve the problems of not considering the impact of supply and demand in the future time period, low travel volume, and affecting the supply and demand environment, etc., to achieve Reduce urban congestion and motor vehicle exhaust emissions, increase travel volume, and improve service quality

Active Publication Date: 2021-08-31
SOUTHWESTERN UNIV OF FINANCE & ECONOMICS
View PDF4 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the scheduling strategy of the previous time period will affect the supply and demand environment of the next and future time periods
For the isolated strategy optimization method based on time period, it does not consider the supply and demand situation in the future time period and the impact of the implemented strategy
Then under this method, the optimal strategy in this time period may not necessarily lead to a higher actual travel volume in the future, and may even cause a lower actual travel volume in the future

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Shared bicycle scheduling method based on deep reinforcement learning
  • Shared bicycle scheduling method based on deep reinforcement learning
  • Shared bicycle scheduling method based on deep reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0059] Embodiments of the present invention will be further described below in conjunction with the accompanying drawings.

[0060] Before describing the specific embodiments of the present invention, in order to make the scheme of the present invention more clear and complete, at first the abbreviations and key term definitions that appear in the present invention are explained:

[0061] OD traffic volume: refers to the traffic volume between the origin and destination. "O" comes from English ORIGIN, pointing out the starting point of the trip, and "D" comes from English DESTINATION, pointing out the destination of the trip.

[0062] MFMARL algorithm: Mean Field Multi-Agent Reinforcement Learning, a multi-agent reinforcement learning algorithm based on mean field game theory.

[0063] Such as figure 1 As shown, the present invention provides a kind of shared bicycle scheduling method based on deep reinforcement learning, comprising the following steps:

[0064] S1: Divide ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a shared bicycle scheduling method based on deep reinforcement learning, and the method comprises the following steps: S1, dividing a scheduling region of a shared bicycle, obtaining a scheduling region unit, and determining an operation environment variable of the shared bicycle; S2, determining a scheduling variable of the shared bicycle; S3, constructing a bicycle scheduling optimization model of the shared bicycles; S4, on the basis of the bicycle scheduling optimization model of the shared bicycles, constructing a shared bicycle scheduling framework by using a mean field theory, and completing the scheduling of the shared bicycles by using the shared bicycle scheduling framework. The shared bicycle scheduling optimization method based on reinforcement learning provided by the invention is beneficial to intelligently solving the problem of short-term and long-term scheduling optimization of shared bicycles in a large-scale road network in a random and complex dynamic environment. The method considers the supply and demand change of the environment and the interaction influence between the scheduling decision and the environment in the future time, does not need to predict the demand in advance or carry out manual data processing, and is not influenced by the demand prediction calculation efficiency and accuracy.

Description

technical field [0001] The invention belongs to the technical field of vehicle scheduling, and in particular relates to a shared bicycle scheduling method based on deep reinforcement learning. Background technique [0002] In previous studies, the usual way to solve the bicycle scheduling optimization problem is to divide the scheduling time into different time periods, and then independently search for the best scheduling strategy in each divided time period. However, the scheduling strategy of the previous time period will affect the supply and demand environment of the next and future time periods. For the isolated strategy optimization method based on time period, it does not consider the supply and demand situation of future time period and the impact of the implemented strategy. Then under this method, the optimal strategy in this time period may not necessarily lead to a higher actual travel volume in the future, and may even cause a lower actual travel volume in the...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q10/04G06Q10/06G06Q50/30G06F30/15G06F30/27G06N3/04G06N3/08G06F111/04G06F111/08G06F119/12
CPCG06Q10/04G06Q10/06315G06F30/15G06F30/27G06N3/04G06N3/084G06F2111/04G06F2111/08G06F2119/12G06Q50/40Y02T10/40
Inventor 肖峰涂雯雯
Owner SOUTHWESTERN UNIV OF FINANCE & ECONOMICS
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products