Short-term prediction of parking availability in an open parking lot

Abstract

The parking of cars is a globally recognized problem, especially at locations where there is a high demand for empty parking spaces. Drivers tend to cruise additional distances while searching for empty parking spaces during peak hours leading to problems, such as pollution, congestion, and driver frustration. Providing short-term predictions of parking availability would facilitate the driver in making informed decisions and planning their arrival to be able to choose parking locations with higher availability. Therefore, the aim of this study is to provide short-term predictions of available parking spaces with a low volume of data. The open parking lot provides parking spaces free of charge and one such parking lot, located beside a shopping center, was selected for this study. Parking availability data for 21 days were collected where 19 days were used for training, while multiple periods of the remaining 2 days were used to test and evaluate the prediction methods. The test dataset consists of data from a weekday and a weekend. Based on the reviewed literature, three prediction methods suitable for short-term prediction were selected, namely, long short-term memory (LSTM), seasonal autoregressive integrated moving average with exogenous variables (SARIMAX), and the Ensemble-based method. The LSTM method is a deep learning-based method, while SARIMAX is a regression-based method, and the Ensemble method is based on decision trees and random forest to provide predictions. The performance of the three prediction methods with a low volume of data and the use of visitor trends data as an exogenous variable was evaluated. Based on the test prediction results, the LSTM and Ensemble-based methods provided better short-term predictions at multiple times on a weekday, while the Ensemble-based method provided better predictions over the weekend. However, the use of visitor trend data did not facilitate improving the predictions of SARIMAX and the Ensemble-based method, while it improved the LSTM prediction for the weekend.

Spatiotemporal Clustering of Parking Lots at the City Level for Efficiently Sharing Occupancy Forecasting Models

“…The installation of sensors and other infrastructure for data collection may be costly, as well as the development and maintenance of predictive models. When considering the cost of constructing parking occupancy forecasting models at the city level, one must take into account not only the creation and maintenance of individual models for single parking sites but also the time and resources necessary for implementing city-wide solutions [31].…”

Smart Parking: Enhancing Urban Mobility with Fog Computing and Machine Learning-Based Parking Occupancy Prediction

“…Moreover, finding parking spaces for an ever-growing number of vehicles exacerbates this issue. Drivers seek to find available spots close to their destinations to minimize walking distances, but this search for parking can cause traffic congestion and decrease vehicle speed; some studies have shown that almost 30% of urban traffic is due to drivers searching for parking spots [3]. The issue of traffic congestion and limited parking spaces is becoming a worldwide problem.…”

“…The research by ref. [3] involves a comparison of various prediction methods for parking spaces, including deep learning, standard machine learning, and classical methods. The methods they examined include long short-term memory from deep learning, seasonal autoregressive integrated moving average as a classical method, and the ensemble-based decision trees as a general method of deep learning.…”

Stochastic modeling and adaptive forecasting for parking space availability with drivers’ time-varying arrival/departure behavior

“…In the recent years, various deep learning algorithms are used to forecast parking space availability. For example, Fan et al (2022) and Paidi (2022) use the long short-term memory (LSTM)…”