基于LSTM的共享单车真实需求预测方法研究
DOI:
作者:
作者单位:

1.内蒙古大学;2.内蒙古大学 经济管理学院

作者简介:

通讯作者:

中图分类号:

U484

基金项目:

国家自然科学(71961025);内蒙古自然科学(2023MS07005)


Research on real demand prediction method of shared bike based on LSTM
Author:
Affiliation:

1.Inner Mongolia University;2.College of Economics and Management,Inner Mongolia University

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    共享单车是城市交通的重要组成部分。共享单车用户需求的随机性导致其时空需求不均衡,甚至出现“借车难”现象,无法满足高峰时段的用户需求。因此出现高频用户高频出行时段到临近站点借车的现象,这意味着存在隐性需求。对于隐性需求,本文首先应用租借数和归还数刻画站点状态变化,通过挖掘临近站点用户出行情况判断参考站点的临界状态,建立基于站点状态变化图和需求判定模型确定站点的隐性需求。进而依据站点真实需求,建立长短期记忆网络预测模型,并建立基于真实需求的共享单车区域调度模型。该模型以成本最小为目标,通过遗传算法求解得到调度成本最小的路径,为基于真实需求开展平衡调度提供了参考。结果显示,在相近的运输成本下,真实需求下的调度方式能在一定程度上缓解用户借车难的问题,从而减少高频用户的流失。

    Abstract:

    Shared bikes represent a crucial component of urban transportation. The randomness of user demand for shared bikes with fixed piles leads to unbalanced demand in time and space, and even the difficulty in renting a bike, which cannot meet the user demand during peak hours. Therefore, high-frequency users frequently travel to nearby stations to rent a bike for serving, which means that there are implicit demands. To ascertain the implicit needs of the station and to determine the critical status of the reference station for judging the traveling condition of the users in the neighboring station is also mined, and the implicit demand of the station is also obtained based on the change of the state map of the station and the demand determination model. Then, according to the real demand of the station, the Long Short-Term Memory and regional scheduling model based on the real demand are established. The model aims to identify the optimal path with the lowest scheduling cost, which is determined through a genetic algorithm. This approach provides a reference for balanced scheduling based on real demand. The results demonstrate that, when transportation costs are similar, the scheduling method under real demand can alleviate the problem of users' difficulty in renting a bike, thereby reducing the loss of high-frequency users.

    参考文献
    相似文献
    引证文献
引用本文

瑜,张梦蝶. 基于LSTM的共享单车真实需求预测方法研究[J]. 科学技术与工程, , ():

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2023-10-08
  • 最后修改日期:2024-05-23
  • 录用日期:2024-05-29
  • 在线发布日期:
  • 出版日期:
×
亟待确认版面费归属稿件,敬请作者关注