Prediction of Vacant Parking Spaces in the City based on LSTM

Authors

  • Yuhao Zhang

DOI:

https://doi.org/10.62051/1kcvvz44

Keywords:

Parking spaces; LSTM; prediction.

Abstract

With the continuous progress of modern society, more and more families have their own private cars for the convenience of travel and other needs, making it easier and faster to go anywhere. However, with the increase in the number of private cars, parking spaces in parking lots cannot keep up with the growing number of cars. It is increasingly difficult to find parking spaces everywhere when driving, and even if they are found, they are often full. The problems of chaotic management in parking lots have become more serious, greatly affecting people's pace of life. This study aims to predict the vehicle access situation of a parking lot in the future by constructing a prediction model. Based on the collected information of nearly 9,000 vehicles entering and leaving a parking lot, this paper uses the LSTM model to analyze the data by comparing the entry and exit times of different vehicles and whether the vehicles leave the parking lot, and obtain a highly fitted parameter model. The results show that the distribution state of the fitted value of the model is quite close to the real value. The model predicts the data of different time periods in the next 6 days, and obtains relatively accurate prediction results.

Downloads

Download data is not yet available.

References

Ge Caicui. Analysis of the Current Situation and Suggestions for the Development of Smart Transportation in China. Journal of Highway and Transportation Research and Development (Applied Technology Edition), 2013, 9(6): 224-227.

Sun Xiaxia, Liu Jia. Development Status, Prospects, and Countermeasures of the Smart Parking Industry. China High-Tech, 2021, 9: 126-127.

Shao Chunfu. Key Issues and Countermeasures in the Development of Urban Transportation in China. Journal of Beijing Jiaotong University, 2016, 40(4): 32-36.

Yang Lunan, Zhang Haowen, Xu Yizhe, et al. Research on Solutions to Low Utilization Rate of Parking Lots under Information Asymmetry - Taking Wuhan City as an Example. Modern Business Trade Industry, 2021, 42(23): 94-96.

Zhu Huibin. Exploring Urban Smart Transportation Strategies. Jiangnan Forum, 2022, 7: 43-46.

Wu Chunhui. Application of Big Data Technology in City-level Smart Parking Platforms. New Industrialization, 2022, 12(9): 229-232.

Cong Shun, Dong Yi. Current Status and Prospect Analysis of Smart Parking Applications. Auto Time, 2023, 5: 31-33.

Wang Wei. Innovation and Application Exploration of Smart Parking Platforms under Static Traffic Big Data Systems. Electronic Test, 2022, 2: 76-78.

Zhang Wen. Research on Smart Parking Solutions in the Era of Big Data. Information & Communications, 2020, 5: 260-261.

Liu Donghui, Xiao Xue, Zhang Jue. A Short-term Parking Demand Prediction Method Based on Particle Swarm Optimization and LSTM Model with Variable Intervals. Journal of Transport Information and Safety, 2021, 39(4): 77-83.

Downloads

Published

12-08-2024

How to Cite

Zhang, Y. (2024) “Prediction of Vacant Parking Spaces in the City based on LSTM”, Transactions on Computer Science and Intelligent Systems Research, 5, pp. 633–639. doi:10.62051/1kcvvz44.