Dalarna University's logo and link to the university's website

du.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • chicago-author-date
  • chicago-note-bibliography
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Short-term prediction of parking availability in an open parking lot
Dalarna University, School of Information and Engineering.ORCID iD: 0000-0002-2078-3327
(English)Manuscript (preprint) (Other academic)
Abstract [en]

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 was 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. TheLSTM 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 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.

Keywords [en]
parking, prediction, open parking lot, deep learning
National Category
Transport Systems and Logistics Computer Sciences
Identifiers
URN: urn:nbn:se:du-41135OAI: oai:DiVA.org:du-41135DiVA, id: diva2:1647723
Available from: 2022-03-28 Created: 2022-03-28 Last updated: 2023-03-17Bibliographically approved
In thesis
1. Parking support model for open parking lots
Open this publication in new window or tab >>Parking support model for open parking lots
2022 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

Parking is a common process performed by vehicle drivers when they arrive at their destination. It is considered to be the last mile transportation problem of personal vehicles. Some of the common problems observed by drivers are additional cruising, congestion, pollution, and driver frustration. This thesis is focused on open parking lots that provide free parking spaces. Since parking spaces are provided free, open parking lots are in high demand leading to additional cruising and pollution. One of the primary reasons for these problems is the lack of information on parking availability. Such information can be provided using a parking support model, or a smart parking system. As open parking lots do not provide any direct return on investments, no parking support models were available on the market. Therefore, this thesis aims to develop a parking support model suitable for open parking lots which can facilitate in providing real-time and short-term forecast of parking availability. This thesis also examines the magnitude of additional cruising and CO2 emissions observed in an open parking lot. A thermal camera was utilized for collecting data on open parking lots as it is not susceptible to varying illumination and environmental conditions. Since there were no pre-trained algorithms for enabling object detection using thermal camera images, a dataset was created with varying environmental and illumination conditions. This dataset was utilized by deep learning algorithms to facilitate multi-object, real-time detection. The developed parking support model facilitates in providing a real-time and short-term forecast of parking availability. Despite the use of low volume of data, the methods utilized in this thesis facilitated providing better detection and forecasting results. Algorithms, such as ResNet18 and Yolo, facilitated in providing real-time, multi-object detection with high accuracy. Similarly, a short-term forecast of parking availability was provided for the open parking lot using methods such as the Ensemble-based method, LSTM and SARIMAX. Ensemble-based method and LSTM provided better test prediction results with lower errors compared to SARIMAX. A new CO2 emissions model was proposed to estimate the magnitude of emissions observed at an open parking lot. The mean CO2 emissions of additional cruising is 2.7 times more than optimal cruising. Despite the individual CO2 emissions of vehicles being lower, aggregating CO2 emissions from multiple vehicles leads to higher pollution. This problem can be reduced by utilizing the parking support model.

Place, publisher, year, edition, pages
Borlänge: Högskolan Dalarna, 2022
Series
Dalarna Doctoral Dissertations ; 21
Keywords
parking, deep learning, pollution, cruising, detection, tracking, forecasting
National Category
Transport Systems and Logistics Computer and Information Sciences
Identifiers
urn:nbn:se:du-41094 (URN)978-91-88679-36-9 (ISBN)
Public defence
2022-06-03, room 311, 10:30 (English)
Opponent
Supervisors
Available from: 2022-05-03 Created: 2022-03-24 Last updated: 2023-08-17Bibliographically approved

Open Access in DiVA

fulltext(934 kB)206 downloads
File information
File name FULLTEXT01.pdfFile size 934 kBChecksum SHA-512
0d2a055599ed67c5af3aafad2faf8c3e281c76c9eb236b76811131e2a4c7512a9d334399c57bcde67384eb3ba02117e18d573caced482b313d23375b3ab994bc
Type fulltextMimetype application/pdf

Authority records

Paidi, Vijay

Search in DiVA

By author/editor
Paidi, Vijay
By organisation
School of Information and Engineering
Transport Systems and LogisticsComputer Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 206 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 214 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • chicago-author-date
  • chicago-note-bibliography
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf