A Method of Bike Sharing Demand Forecasting

2014 ◽  
Vol 587-589 ◽  
pp. 1813-1816 ◽  
Author(s):  
Xiao Na Liu ◽  
Jian Jun Wang ◽  
Teng Fei Zhang
Keyword(s):  
Short Distance ◽  
Demand Forecasting ◽  
Public Transport System ◽  
Urban Public Transport ◽  
Bike Sharing ◽  
Private Car ◽  
Using Data ◽  
Turn Over ◽  
Distance Travel ◽  
Travel Rate

Bike sharing system is an important part of urban public transport system, mainly to undertake the function of connection and transfer with bus system, and connection with private car and satisfy the demand of citizen short-distance travel, and other functions. Setting bike sharing rental point is according to the planning of urban comprehensive transportation, using data on the residents travel , including travel rate, traffic structure, etc. and then to predict the proportion of future bike sharing to the total amount of travel, finally obtain bike sharing overall scale combining Bike sharing turn over rate.

Yulu: Moving Towards a Sustainable Future

2020 ◽  
Vol 9 (3) ◽  
pp. 445-456
Author(s):  
Deepika Upadhyay ◽  
Geetanjali Purswani ◽  
Pooja Jain
Keyword(s):  
Air Pollution ◽  
Traffic Congestion ◽  
Short Distance ◽  
Management Practices ◽  
Alternative Mode ◽  
Final Destination ◽  
Metropolitan Cities ◽  
The World ◽  
Bike Sharing ◽  
Distance Travel

The rapidly rising rate of urbanization, which is closely linked to economic growth, has exposed the world to several challenges such as inequality, environmental degradation, traffic congestion, infrastructural concerns and social conflicts. Therefore, urban sustainability has emerged as one of the most debatable discussions across the world. The existing network of transportation can no longer keep up with the growing demand in metropolitan cities. Short distance travel has become an unresolved issue for daily commuters. The case presents how MMVs have emerged as an alternative mode of transport for resolving issues of daily commuters regarding the first-mile connectivity, last-mile connectivity and short distance travel to reach their final destination. MMVs are basically light-weight vehicles which occupy less space on road. These vehicles include bicycles, e-bikes, skateboards, hoverboards and other battery-operated vehicles. The case narrates the journey of Yulu, a dockless bike-sharing venture which promoted the concept of green consumerism among the daily commuters at affordable rates. The venture initially started in the IT city of Bangalore and later expanded its operations to other cities such as Pune, Navi Mumbai, Gurugram and Bhubaneswar. The speciality of this venture is that it offers a sustainable solution to ever-increasing problems of traffic congestion and aggravating air pollution issues in metropolitan cities. Dilemma: How to offer a sustainable solution to the ever-increasing problem of traffic congestion and aggravating air pollution due to rising vehicular traffic? How to make short distance travel affordable and more convenient for daily commuters? Theory: Three pillars of sustainable development. Type of Case: Problem solving applied case. Protagonist: Present. Discussion and Case Questions: What strategies should be employed by the start-up to make it a more popular form of commute? How can the increasing rate of damage to the vehicles be brought down? How does organization structure and cluster management practices of Yulu help it to become more sustainable? How can the regulatory bodies and government promote and adopt such start-ups in their urban planning projects?

Enhancing the Accuracy of Peak Hourly Demand in Bike-Sharing Systems using a Graph Convolutional Network with Public Transit Usage Data

2021 ◽  
pp. 036119812110120
Author(s):  
Jung-Hoon Cho ◽  
Seung Woo Ham ◽  
Dong-Kyu Kim
Keyword(s):  
Adjacency Matrix ◽  
Public Transit ◽  
Demand Forecasting ◽  
The Other ◽  
Convolutional Network ◽  
Demand Pattern ◽  
Temporal Features ◽  
Unmet Demand ◽  
Bike Sharing ◽  
Main Component

With the growth of the bike-sharing system, the problem of demand forecasting has become important to the bike-sharing system. This study aims to develop a novel prediction model that enhances the accuracy of the peak hourly demand. A spatiotemporal graph convolutional network (STGCN) is constructed to consider both the spatial and temporal features. One of the model’s essential steps is determining the main component of the adjacency matrix and the node feature matrix. To achieve this, 131 days of data from the bike-sharing system in Seoul are used and experiments conducted on the models with various adjacency matrices and node feature matrices, including public transit usage. The results indicate that the STGCN models reflecting the previous demand pattern to the adjacency matrix show outstanding performance in predicting demand compared with the other models. The results also show that the model that includes bus boarding and alighting records is more accurate than the model that contains subway records, inferring that buses have a greater connection to bike-sharing than the subway. The proposed STGCN with public transit data contributes to the alleviation of unmet demand by enhancing the accuracy in predicting peak demand.

scholarly journals A Multiperiodic Optimization Formulation for the Operation Planning of Free-Floating Shared Bike in China

2018 ◽  
Vol 2018 ◽  
pp. 1-11 ◽  
Author(s):  
Meiyu Li ◽  
Xifu Wang ◽  
Xi Zhang ◽  
Lifen Yun ◽  
Yuan Yuan
Keyword(s):  
Optimization Model ◽  
Short Distance ◽  
Planning Horizon ◽  
Mobile Payment ◽  
Operation Planning ◽  
The Public ◽  
Optimization Formulation ◽  
Bike Sharing ◽  
Minimum Number ◽  
Time Periods

Internet shared bike has trigged a revolution on the public bicycle utilization in China for various characteristics such as free-floating, intelligent unlocking, mobile payment, intelligent integration, and optional serving. It attracts many users and meanwhile accumulates the development of short-distance alternative trip. This paper has designed an optimization model for the deployment and travel of free-floating bike sharing (FFBS) among small regions. For a given demand under the constraint of overload of flexile stations, the model makes a decision on the minimum number of bike deployments in the system and the planning of bike movement between stations at different time periods. It maximizes the profit of operators during the whole planning horizon and meanwhile satisfices the demand and minimizes the overload situation of stations. The proposed approach is verified with numerical example, aiming to help operators to program and manage systems in a more efficient way.

Planned Traffic Stability on a Rail Network

2015 ◽  
Vol 809-810 ◽  
pp. 1073-1078 ◽  
Author(s):  
Cristina Ștefănică ◽  
Vasile Dragu ◽  
Ştefan Burciu ◽  
Anamaria Ilie ◽  
Oana Dinu
Keyword(s):  
Public Transport ◽  
Road Traffic ◽  
Discrete Event ◽  
Elimination Rate ◽  
Integrated Network ◽  
Rail Network ◽  
Urban Public Transport ◽  
Private Car ◽  
Event Dynamic ◽  
The Stability

Impetuous multiplication of mobility and road traffic proliferation lead to concerns for increasing the attractiveness of urban public transport. Compared to private car use, urban public transport attractiveness is conditioned, in particular, by travel times and certainty of respecting the transport schedules, meaning planned traffic stability. Traffic schedules are considered to be more stable as the primary delays from the announced schedule have low probabilities and values and their propagation as repeated delays is least noticed in time and space. Solutions for assuring traffic stability must take into consideration contradictory aspects, because introducing time reserves in the schedules means time travel extensions. In order to assure the stability of planned traffic, present paper develops studies of various models and methods that aim to reduce inherent primary delays. Thereby, for studying repeated delays on a complex network, a mathematical model adequate to a Discrete Event Dynamic System (DEDS), that in MAX-PLUS algebra becomes a linear system, was used. The paper concludes with a case study on an integrated network resulted from the superposition of Bucharest’s existing suburban rail network with the underground network designed for 2030, being identified measures for improving the stability indicators. Traffic stability is assessed on the basis of two indicators: instability coefficient and delay elimination rate. Main measure for improving stability indicators is the growth of time reserves taking into consideration the quality requirements resulting from the condition of maintaining a reduced planned travel time.

scholarly journals Identification of Prior Factors Influencing the Mode Choice of Short Distance Travel

2015 ◽  
Vol 2015 ◽  
pp. 1-9 ◽  
Author(s):  
Ming Li ◽  
Guohua Song ◽  
Ying Cheng ◽  
Lei Yu
Keyword(s):  
Traffic Congestion ◽  
Household Income ◽  
Short Distance ◽  
Structural Equation ◽  
Mode Choice ◽  
Equation Modeling ◽  
Residential Areas ◽  
Factors Influencing ◽  
Willingness To Change ◽  
Distance Travel

Short distance trips are defined as any trips shorter than or equal to 5 kilometers, which have been found to be a big contributor to the traffic congestion problem. This paper is intended to analyze factors that influence the mode choice of short distance travels in order to help reduce short distance trips by cars. A survey is conducted at two typical kinds of residential areas, one with a high proportion of short distance car trips and another one with a low proportion. Then, by applying the structural equation modeling, it is found that the age, the household income, and the vehicle ownerships have a significant effect on the mode choice of short distance travels. Besides, among residents of the same type (same age, household income, and vehicle ownerships) in surveyed areas, those in the area with a better green-mode travel environment account for a higher proportion choosing the green mode than those in other areas. Based on this result, it is concluded that a better green-mode travel environment leads to a higher proportion of green-mode travels. In the end, the paper shows residents’ stated willingness to change travel modes from cars to the green mode.

scholarly journals Dynamic Scheduling Model of Bike-Sharing considering Invalid Demand

2020 ◽  
Vol 2020 ◽  
pp. 1-10
Author(s):  
Liu He ◽  
Tangyi Guo ◽  
Kun Tang
Keyword(s):  
Optimization Model ◽  
Dynamic Scheduling ◽  
Demand Forecasting ◽  
Optimal Solution ◽  
Coupling Model ◽  
Service Level ◽  
Demand Prediction ◽  
Dynamic Relationship ◽  
Proposed Model ◽  
Bike Sharing

System resources allocation optimization through dynamic scheduling is key to improving the service level of bike-sharing. This study innovatively introduces three types of invalid demand with negative effect including waiting, transfer, and abandoning, which consists of the total demand of bike-sharing system. Through exploring the dynamic relationship among users’ travel demands, the quantity and capacity of bikes at the rental points, the records of bicycles borrowed and returned, and the vehicle scheduling schemes, a demand forecasting model for bike-sharing is established. According to the predicted bikes and the maximum capacity limit at each rental point, an optimization model of scheduling scheme is proposed to reduce the invalid demand and the total scheduling time. A two-layer dynamic coupling model with iterative feedback is obtained by combining the demand prediction model and scheduling optimization model and is then solved by Nicked Pareto Genetic Algorithm (NPGA). The proposed model is applied to a case study and the optimal solution set and corresponding Pareto front are obtained. The invalid demand is greatly reduced from 1094 to 26 by an effective scheduling of 3 rounds and 96 minutes. Empirical results show that the proposed model is able to optimize the resource allocation of bike-sharing, significantly reduce the invalid demand caused by the absence of bikes at the rental point such as waiting in a place, walking to other rental points, and giving up for other travel modes, and effectively improve the system service level.

Sign in / Sign up

Export Citation Format

Share Document