A Bimodal Gaussian Inhomogeneous Poisson Algorithm for Bike Number Prediction in a Bike-Sharing System

Huang, Feihu; Qiao, Shaojie; Peng, Jian; Guo, Bing

doi:10.1109/tits.2018.2868483

Cited by 31 publications

(15 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a bike sharing system, the process by which customers arrive at a station to rent or return bikes can be described by the Poisson process [43]. The renting intensity of Poisson process Rent i,k corresponds to the total number of customers who rent at station S i during time t(k).…”

Section: The Optimal State Calculatingmentioning

confidence: 99%

“…As discussed before, for each station in a BSS, the arrival processes of customers for renting and returning can be described by the Poisson process [43], which indicates that the time interval between two adjacent events should obey the exponential distribution. We analyzed the time interval distribution of the experimental data and found that most of the stations followed the exponential distribution.…”

Section: Parameter Settingmentioning

confidence: 99%

“…One is the customers' arrival process for renting at a station and the other is the arrival process for returning. Previous studies [42,43] have demonstrated that these two processes can be described by the inhomogeneous Poisson process.…”

mentioning

confidence: 97%

See 2 more Smart Citations

A Rebalancing Strategy for the Imbalance Problem in Bike-Sharing Systems

Huang

Peng

2019

Energies

Self Cite

View full text Add to dashboard Cite

Shared bikes have become popular traveling tools in our daily life. The successful operation of bike sharing systems (BSS) can greatly promote energy saving in a city. In BSS, stations becoming empty or full is the main cause of customers failing to rent or return bikes. Some truck-based rebalancing strategies are proposed to solve this problem. However, there are still challenges around the relocation of bikes. The truck operating costs also need to be considered. In this paper, we propose a customer-oriented rebalancing strategy to solve this problem. In our strategy, two algorithms are proposed to ensure the whole system is balanced for as long as possible. The first algorithm calculates the optimal state of each station through the one-dimensional Random Walk Process with two absorption walls. Based on the derived optimal state of each station, the second algorithm recommends the station that has the largest difference between its current state and its optimal state to the customer. In addition, a simulation system of shared bikes based on the historical records of Bay Area Bikeshare is built to evaluate the performance of our proposed rebalancing strategy. The simulation results indicate that the proposed strategy is able to effectively decrease the imbalance in the system and increase the system’s performance compared with the truck-based methods.

show abstract

Section: The Optimal State Calculatingmentioning

confidence: 99%

Section: Parameter Settingmentioning

confidence: 99%

See 1 more Smart Citation

A Rebalancing Strategy for the Imbalance Problem in Bike-Sharing Systems

Huang

Peng

2019

Energies

Self Cite

View full text Add to dashboard Cite

show abstract

“…Many researchers have proposed lots of algorithms for dynamic scheduling of bicycle sharing systems. Huang et al [23] proposed an algorithm called Bimodal Gaussian Inhomogeneous Poisson (BGIP) to predict the number of bikes. It can help to optimize the repository of bikes.…”

Section: Related Workmentioning

confidence: 99%

A Novel Dynamic Dispatching Method for Bicycle-Sharing System

Mao¹,

Hao²,

Wang³

et al. 2019

IJGI

View full text Add to dashboard Cite

With the rapid development of sharing bicycles, unreasonable dispatching methods are likely to cause a series of issues, such as resource waste and traffic congestion in the city. In this paper, a new dynamic scheduling method is proposed, named Tri-G, so as to solve the above problems. First of all, the whole visualization information of bike stations was built based on a Spatio-Temporal Graph (STG), then Gaussian Mixture Mode (GMM) was used to group individual stations into clusters according to their geographical locations and transition patterns, and the Gradient Boosting Regression Tree (GBRT) algorithm was adopted to predict the number of bikes inflow/outflow at each station in real time. This paper used New York’s bicycle commute data to build global STG visualization information to evaluate Tri-G. Finally, it is concluded that Tri-G is superior to the methods in control groups, which can be applied to various geographical scenarios. In addition, this paper also discovered some human mobility patterns as well as some rules, which are helpful for governments to improve urban planning.

show abstract

“…To the best of our knowledge, this study is the first one that could predict both usage and bike amount with only journey data, by converting journey data into the time series of bike distribution. As an example of former researches, Huang et al [28] predicted bike distribution with both bike count data and journey data. In this paper, we formulate a novel framework for DBS usage and bike count prediction using only journey data.…”

Section: Introductionmentioning

confidence: 99%