期刊
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
卷 593, 期 -, 页码 -出版社
ELSEVIER
DOI: 10.1016/j.physa.2022.126925
关键词
Free-floating bike-sharing; Repositioning; Optimization; Gaussian mixture model; NSGA-II; TOPSIS
资金
- Innovation-Driven Project of Central South University, China [2020CX041]
- Humanities and Social Sciences Foundation of the Ministry of Education [21YJCZH147]
- National Natural Science Foundation of China [52172310]
This study introduces an improved repositioning model for the free-floating bike-sharing system and designs Non-dominated Sorting Genetic Algorithm II (NSGA-II) to conduct optimization. The proposed method, which adopts Gaussian mixture model (GMM) for clustering and establishes a multi-objective optimization model, is reasonable and effective in reposition optimization for free-floating bike-sharing system.
In recent years, the free-floating bike-sharing system has attracted a large number of travelers for its convenience and non-pollution in the urban public transit. Although many researchers have been carried out, there still exist challenges in repositioning optimization to improve the operating efficiency in the bike-sharing system. This study introduces an improved repositioning model for the free-floating bike-sharing system and designs Non-dominated Sorting Genetic Algorithm II (NSGA-II) to conduct optimization. Firstly, the Gaussian mixture model (GMM) is adopted for clustering to obtain the stations in the free-floating bike-sharing system. Then, a multi-objective optimization model is established considering minimizing the total cost of the repositioning operation and maximizing the satisfaction degree of demands of the delivery stations. To solve the model, an improved NSGA-II is proposed, in which different ways of crossover and mutation operators are applied to maintain the diversity of the population. The Technique for Order Preference by Similarity to an Ideal Solution (TOPSIS) is used to determine the best compromise solution. Finally, using trajectory data from the freefloating bike-sharing system in Shenzhen City, we further compare the results with traditional Genetic Algorithm (GA). The comparison demonstrates that the proposed method is reasonable and effective in the reposition optimization for free-floating bike-sharing system. (c) 2022 Elsevier B.V. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据