Abstract
The smart city concept refers principally to employing technology to deal with different problems surrounding the city and the citizens. Urban mobility is one of the most challenging aspects considering the logistical complexity as well as the ecological relapses. More specifically, parking is a daily tedious task that citizens confront especially considering the large number of vehicles compared to the limited parking, the rush hours peaks, etc. Forecasting parking occupancy might allow citizens to plan their parking better and therefore enhance their mobility. Time-series forecasting methods have proved their efficiency for such tasks, and this work goes in the same line by exploring how to provide more accurate parking occupancy forecasting. Concretely, its contributions stand in a complete pipeline, including (I) the automatic extra-transform-load data module and (II) the time-series forecasting methods themselves, where four have been studied: one additive regression model (Prophet), the Seasonal Auto-Regressive Integrated Moving Average (SARIMAX), and two deep learning models, the Long Short Term memory neural networks (LSTM), and Neural Prophet. Experiments have been performed on data of 3 and 28 parking from the city of Malaga (Spain) and Birmingham (England) using data recorded through 6 months (June-November 2022) and two and a half months (October-December, 2016), for Malaga and Birmingham, respectively. The results showed that Prophet provided very competitive results compared to the literature.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
World Cities’ Statistics: https://ourworldindata.org/urbanization.
- 2.
Vehicles Statistics: https://en.wikipedia.org/wiki/List_of_countries_by_vehicles_per_capita.
- 3.
Malaga City Hall API: https://datosabiertos.malaga.eu/dataset/ocupacion-aparcamientos-publicos-municipales.
- 4.
Malaga parking history data: https://github.com/javisenberg/malaga-parking-data.
- 5.
References
The proposed parking occupancy forecasting prototype. https://github.com/NEO-Research-Group/Parking-Ocuppancy-Forcasting.git. Accessed 27 Jan 2023
Amato, G., Carrara, F., Falchi, F., Gennaro, C., Meghini, C., Vairo, C.: Deep learning for decentralized parking lot occupancy detection. Expert Syst. Appl. 72, 327–334 (2017)
Banaś, J., Utnik-Banaś, K.: Evaluating a seasonal autoregressive moving average model with an exogenous variable for short-term timber price forecasting. Forest Policy Econ. 131, 102564 (2021)
Camero, A., Toutouh, J., Stolfi, D.H., Alba, E.: Evolutionary deep learning for car park occupancy prediction in smart cities. In: Battiti, R., Brunato, M., Kotsireas, I., Pardalos, P.M. (eds.) LION 12 2018. LNCS, vol. 11353, pp. 386–401. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-05348-2_32
Camero, A., Alba, E.: Smart city and information technology: a review. Cities 93, 84–94 (2019)
Cintrano, C., Ferrer, J., López-Ibáñez, M., Alba, E.: Hybridization of evolutionary operators with elitist iterated racing for the simulation optimization of traffic lights programs. Evolut. Comput. 1–21 (2022)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Nath, P., Saha, P., Middya, A.I., Roy, S.: Long-term time-series pollution forecast using statistical and deep learning methods. Neural Comput. Appl. 33(19), 12551–12570 (2021). https://doi.org/10.1007/s00521-021-05901-2
Parmezan, A.R.S., Souza, V.M., Batista, G.E.: Evaluation of statistical and machine learning models for time series prediction: Identifying the state-of-the-art and the best conditions for the use of each model. Inf. Sci. 484, 302–337 (2019)
Stolfi, D.H., Alba, E., Yao, X.: Predicting car park occupancy rates in smart cities. In: Alba, E., Chicano, F., Luque, G. (eds.) Smart Cities. Smart-CT 2017. LNCS, vol. 10268, pp. 107–117. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-59513-9_11
Stolfi, D.H., Alba, E., Yao, X.: Can i park in the city center? predicting car park occupancy rates in smart cities. J. Urban Technol. 27(4), 27–41 (2020)
Taylor, S.J., Letham, B.: Forecasting at scale. Am. Stat. 72(1), 37–45 (2018)
Triebe, O., Hewamalage, H., Pilyugina, P., Laptev, N., Bergmeir, C., Rajagopal, R.: Neuralprophet: explainable forecasting at scale (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Morell, J.Á., Dahi, Z.A., Chicano, F., Luque, G., Alba, E. (2023). Time Series Forecasting for Parking Occupancy: Case Study of Malaga and Birmingham Cities. In: Dorronsoro, B., Chicano, F., Danoy, G., Talbi, EG. (eds) Optimization and Learning. OLA 2023. Communications in Computer and Information Science, vol 1824. Springer, Cham. https://doi.org/10.1007/978-3-031-34020-8_28
Download citation
DOI: https://doi.org/10.1007/978-3-031-34020-8_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-34019-2
Online ISBN: 978-3-031-34020-8
eBook Packages: Computer ScienceComputer Science (R0)