Real Time Short-term Forecasting Method of Remaining Parking Space in Urban Parking Guidance Systems

Zhu, Xiaogang; Guo, Jianhua; Huang, Wei; Yu, Fengquan; Park, Byungkyu Brian

doi:10.7307/ptt.v30i2.2388

Cited by 3 publications

(1 citation statement)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In various time series analysis studies on parking space prediction, variants of ARIMA have achieved valuable results. For example, Zhu et al applied an ARIMA model with an additional real-time short-term forecasting framework to create a parking guidance system in Nanjing, China, which outperformed both a conventional neural network method and the Markov chain method (14). Friso et al implemented seasonal ARIMA in a short-term traffic prediction case study that, despite its simplicity, obtained more accurate results than more complicated methods like multivariate spatial-temporal ARIMA (15).…”

Section: Related Literaturementioning

confidence: 99%

Short-Term Forecasting of Off-Street Parking Occupancy

Fokker

Koch

Leeuwen

et al. 2021

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

Information and communication technologies have opened the way to guide recent developments in the field of parking. In this paper these technologies are applied to model a decision support system that gives insight into 6-months ahead parking occupancy forecasts for 57 off-street parking locations in Amsterdam. An effect analysis was conducted into the influence of weather-, event-, parking tariff-, and public transport attributes on parking occupancy. The most influential factors on the parking occupancy were the scheduling of artistic and sports events, the addition of a public transport line, and the weather variables thunderstorm, average wind speed, temperature, precipitation, and sunshine duration. Parking tariffs did not significantly contribute to model performance, which could have been because of the lack of data and time variability in the parking tariffs of the examined parking locations. The forecasting algorithms compared were the seasonal naive model as a benchmark approach, the Box–Jenkins seasonal autoregressive integrated moving average with and without exogenous regressors (SARIMAX and SARIMA, respectively), exponential smoothing models, and the long short-term memory neural network. The SARIMAX model outperformed the other algorithms for the 6-months ahead forecasts according to the lowest root mean square error (RMSE). By including the event factor, the model improved by 24% based on the RMSE. Weather variables improved the predictive performance by 8%. Future studies could focus on the addition of more event variables, extension into an online model, and the impact of spatial–temporal features on parking occupancy.

show abstract

Section: Related Literaturementioning

confidence: 99%

Short-Term Forecasting of Off-Street Parking Occupancy

Fokker

Koch

Leeuwen

et al. 2021

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

show abstract

Social Signal-Driven Knowledge Automation: A Focus on Social Transportation

Lü

Zhu

Yuan

et al. 2021

IEEE Trans. Comput. Soc. Syst.

View full text Add to dashboard Cite

A numerical model for impacts of left-turn non-motorized vehicles on through lane capacity metrics

Lin

Liu

et al. 2020

AoT

View full text Add to dashboard Cite

There is a conflict between through motor vehicles and the left-turn non-motorized vehicles, and the capacity of straight-line motor vehicles decreases. This study analyzes the impacts of left-turn non-motorized vehicles on the capacity of through motor vehicle lanes. A correction coefficient model for calculating the reduced capacity of through motor vehicle lanes has been developed based on analysis of the conflicting points at an intersection and the negative exponential function of traffic flow distribution. With consideration of intersection geometric design, channelization, and traffic characteristics, the correction coefficient model was further enhanced by regression to capture the impacts of left-turn non-motorized vehicles from the same and the opposite directions. A simulation with VISSIM is used to validate the developed model. It shows that the calculated capacity from the correction coefficient model is close to the simulation results. The experiment indicates that the derived model is highly accurate in calculating the capacity of through motor vehicle lanes and has potential application for situations of mixed traffic in China. The study shows that the capacity of a through traffic lane at the permitted phase decreases with the increase of left-turning non-motorized vehicles, and the impact of left-turning non-motorized vehicles from the same direction is more significant. The results show that the traffic capacity of straight-line motor vehicle decreases with the increase of the left-turn non-motorized vehicles flow rate and the influence of the left-turn non-motor vehicle is more obvious. It is suggested that in practice, the correction coeffi-cient of non-motor vehicle on the left turn should be 0.88, and the correction coefficient on the left turn should be 0.95, respectively. The study recommends coefficient values for both non-motorized vehicles from the same and opposite directions for use in real applications.

show abstract

Real Time Short-term Forecasting Method of Remaining Parking Space in Urban Parking Guidance Systems

Cited by 3 publications

References 28 publications

Short-Term Forecasting of Off-Street Parking Occupancy

Short-Term Forecasting of Off-Street Parking Occupancy

Social Signal-Driven Knowledge Automation: A Focus on Social Transportation

A numerical model for impacts of left-turn non-motorized vehicles on through lane capacity metrics

Contact Info

Product

Resources

About