Free Floating Electric Car Sharing: A Data Driven Approach for System Design

Cocca, Michele; Giordano, Danilo; Mellia, Marco; Vassio, Luca

doi:10.1109/tits.2019.2932809

Cited by 26 publications

(25 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our previous work [17], we analyzed in depth the usage of different car-sharing systems in Vancouver. Based on this data, we developed a model of FFCS usage and built a simulator to design new systems based on electric vehicles [5]. In particular, we tackled the charging station placement problem, showing that the optimal placement requires few stations to satisfy charging requests in different cities [6].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

On Car-Sharing Usage Prediction with Open Socio-Demographic Data

et al. 2020

Self Cite

View full text Add to dashboard Cite

Free-Floating Car-Sharing (FFCS) services are a flexible alternative to car ownership. These transportation services show highly dynamic usage both over different hours of the day, and across different city areas. In this work, we study the problem of predicting FFCS demand patterns—a problem of great importance to the adequate provisioning of the service. We tackle both the prediction of the demand (i) over time and (ii) over space. We rely on months of real FFCS rides in Vancouver, which constitute our ground truth. We enrich this data with detailed socio-demographic information obtained from large open-data repositories to predict usage patterns. Our aim is to offer a thorough comparison of several machine-learning algorithms in terms of accuracy and ease of training, and to assess the effectiveness of current state-of-the-art approaches to address the prediction problem. Our results show that it is possible to predict the future usage with relative errors down to 10%, while the spatial prediction can be estimated with relative errors of about 40%. Our study also uncovers the socio-demographic features that most strongly correlate with FFCS usage, providing interesting insights for providers interested in offering services in new regions.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Armed with good predictions, the provider can better plan long-term system management, e.g., whether to extend the operative area to those neighborhoods with expected customer growth. Similarly, it can implement short-term dynamic relocation policies to better meet the demand in the next hours [4][5][6].…”

Section: Introductionmentioning

confidence: 99%

On Car-Sharing Usage Prediction with Open Socio-Demographic Data

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…In our previous work [18] we analyzed in depth the usage of different car sharing systems in Vancouver. Based on this data we developed a model of FFCS usage and built a simulator to design new systems based on electric vehicles [5]. In particular we tackled the charging station placement problem, showing that the optimal placement requires few stations to satisfy charging requests in different cities [6].…”

Section: Related Workmentioning

confidence: 99%

“…Among those, we manually selected 83 features that might be related to human mobility. 5 Moreover, we also report: i) the distance to downtown -computed as the distance from the neighborhood to the downtown neighborhood (considered as the central area); 6 ii) an indicator of human activity, measured by the number of emergency calls per time bin (obtained from the Vancouver census); and iii) the The use of the Car2go API (https://www.car2go.com/api/tou.htm) is subject to approval by Car2go. We got the approval in September 2016 and continued the collection of data in January 2018.…”

Section: Socio-demographic Weather and Other Open Datamentioning

confidence: 99%

See 1 more Smart Citation

On Car Sharing Usage Prediction with Open Socio-Demographic Data

Cocca¹,

Teixeira²,

Vassio³

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

Free Floating Car Sharing (FFCS) services are a flexible alternative to car ownership. These transportation services show highly dynamic usage both over different hours of the day, and across different city areas. In this work, we study the problem of predicting FFCS demand patterns -- a problem of great importance to an adequate provisioning of the service. We tackle both the prediction of the demand i) over time and ii) over space. We rely on months of real FFCS rides in Vancouver, which constitute our ground truth. We enrich this data with detailed socio-demographic information obtained from large open-data repositories to predict usage patterns. Our aim is to offer a thorough comparison of several machine learning algorithms in terms of accuracy and easiness of training, and to assess the effectiveness of current state-of-art approaches to address the prediction problem. Our results show that it is possible to predict the future usage with relative errors down to 10%, and the spatial prediction can be estimated with relative errors of about 40%. Our study also uncovered the socio-demographic features that most strongly correlate with FFCS usage, providing interesting insights for providers opening service in new regions.

show abstract

Optimal planning of charging stations for an electric vehicle fleet in c ar‐sharing business

Wang

Tang

Lai

et al. 2021

Int Trans Electr Energ Syst

View full text Add to dashboard Cite

Summary With the increasing market share of electric vehicles (EVs), optimizing the planning decisions of charging stations becomes critical to support long‐distance traveling. Besides, the booming car‐sharing industry provides an alternative business model to enhance the utilization of vehicle resources. Recently, several car‐sharing enterprises have launched the collaborations with charging station construction companies to construct their own charging facilities, which calls for the co‐optimization of charging station planning and scheduling of EVs in car‐sharing business. Therefore, this paper develops an optimization model for electric vehicle charging stations placements and type selections, considering routing selection and charging management of an electric vehicle fleet in car‐sharing business. Specifically, a stochastic programming framework is exploited to incorporate a variety of operating scenarios, which reflect the uncertainties of riders' requirements, drivers' itineraries, traffic flow information, and electricity prices. The proposed model aims to improve the welfare of all riders and reduce total cost of fulfilling riders' pickup and delivery requirements simultaneously, in which determining the optimal locations and types of charging facilities is required. Moreover, portfolio management is integrated into the optimization model to mitigate investment risk. After a series of reformulation, the proposed optimization model can be recast into a mixed‐integer linear programming problem. Using two transportation networks, the effectiveness of the proposed model is validated in numerical studies. It finds that the optimal electric vehicle charging station planning strategy is determined according to the operator's preferences, electricity prices, and installation budgets. Moreover, diversity within operating scenarios yields the positive value‐of‐stochastic‐solution that demonstrates the necessity of implementing stochastic programming.

show abstract

Free Floating Electric Car Sharing: A Data Driven Approach for System Design

Cited by 26 publications

References 19 publications

On Car-Sharing Usage Prediction with Open Socio-Demographic Data

On Car-Sharing Usage Prediction with Open Socio-Demographic Data

On Car Sharing Usage Prediction with Open Socio-Demographic Data

Optimal planning of charging stations for an electric vehicle fleet in c ar‐sharing business

Contact Info

Product

Resources

About