Performance analysis of parking occupancy prediction models in an IoT-based intelligent system

Authors

DOI:

https://doi.org/10.18372/2073-4751.81.20126

Keywords:

smart parking system, cloud computing, occupancy forecasting, Internet of Things, LSTM, Prophet, SARIMA, time series analysis, machine learning

Abstract

The article investigates the effectiveness of parking occupancy forecasting models within an Internet of Things (IoT) intelligent system operating on cloud computing principles. The relevance of parking space management in modern urbanization is considered. The architecture of an analytical system is presented, which includes IoT sensors for data collection, a cloud platform for data processing and storage, and a forecasting module. Three time-series forecasting models are described in detail: LSTM (Long Short-Term Memory), Prophet, and SARIMA (Seasonal Autoregressive Integrated Moving Average). An experimental study of these models was conducted on a parking occupancy dataset, including their training, testing, and evaluation using MAE, RMSE, and MAPE metrics. A comparative analysis of the accuracy of the models was performed, identifying the advantages and disadvantages of each in the context of forecasting parking zone occupancy. The research results demonstrate the potential of using machine learning models to optimize urban parking infrastructure management and can be used for further improvement of intelligent transport systems.

References

Channamal S. et al. A review of smart parking systems. Transportation Research Procedia. 2023. Vol. 73. P. 289–296. DOI: 10.1016/j.trpro.2023.11.925.

Fahim A., Hasan M., Chowdhury M. A. Smart parking systems: comprehensive review based on various aspects. Heliyon. 2021. Vol. 7(5). e07050. DOI: 10.1016/j.heliyon.2021.e07050.

Biyik C. et al. Smart Parking Systems: Reviewing the Literature, Architecture and Ways Forward. Smart Cities. 2021. Vol. 4(2). P. 623–642. DOI: 10.3390/smartcities4020032.

Chaturvedi S. et al. A comparative assessment of SARIMA, LSTM RNN and Fb Prophet models to forecast total and peak monthly energy demand for India. Energy Policy. 2022. Vol. 168. 113097. DOI: 10.1016/j.enpol.2022.113097.

Katambire V. N. et al. Forecasting the Traffic Flow by Using ARIMA and LSTM Models: Case of Muhima Junction. Forecasting. 2023. Vol. 5(4). P. 616–628. DOI: 10.3390/forecast5040034.

Goodfellow I., Bengio Y., Courville A. Deep Learning. London : MIT Press, 2016. 800 p.

Taylor S. J., Letham B. Forecasting at scale. The American Statistician. 2018. Vol. 72(1). P. 37–45. DOI: 10.1080/00031305.2017.1380080.

Hyndman R. J., Athanasopoulos G. Forecasting: principles and practice. 2nd ed. OTexts, 2018. 382 p.

Hochreiter S., Schmidhuber J. Long short-term memory. Neural computation. 1997. Vol. 9(8). P. 1735–1780.

Box G. E. P. et al. Time series analysis: forecasting and control. 5th ed. Hoboken : John Wiley & Sons, 2015. 720 p.

Published

2025-06-01

Issue

Section

Статті