An Improved Spatio-Temporal Network Traffic Flow Prediction Method Based on Impedance Matrix

Effective traffic management and congestion reduction heavily rely on accurate traffic flow prediction. Existing prediction methods, such as Markov, ARIMA, STANN, GLSTM, and DCRNN models, often face challenges because they rely on fixed spatial relationships, leading to limited long-term prediction...

Full description

Saved in:
Bibliographic Details
Main Authors: Wenhao Li, Yanyan Chen, Yuyan Pan, Yunchao Zhang
Format: Article
Language:English
Published: Tsinghua University Press 2024-06-01
Series:Journal of Highway and Transportation Research and Development
Subjects:
Online Access:https://www.sciopen.com/article/10.26599/HTRD.2024.9480015
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850069203495682048
author Wenhao Li
Yanyan Chen
Yuyan Pan
Yunchao Zhang
author_facet Wenhao Li
Yanyan Chen
Yuyan Pan
Yunchao Zhang
author_sort Wenhao Li
collection DOAJ
description Effective traffic management and congestion reduction heavily rely on accurate traffic flow prediction. Existing prediction methods, such as Markov, ARIMA, STANN, GLSTM, and DCRNN models, often face challenges because they rely on fixed spatial relationships, leading to limited long-term prediction accuracy. To address these shortcomings, this study proposes the Impedance-Spatio-Temporal Topological Network (Impedance-STTN) prediction model. The Impedance-STTN model integrates K-medoids clustering for data analysis, generating a real-time impedance matrix from impedance functions, traffic big data, and real-time flow data. This approach captures dynamic node relationships within the spatio-temporal network, enhancing prediction accuracy. Experimental results demonstrate the superior predictive performance of the Impedance-STTN model, achieving accuracies of 94.79%, 93.78%, and 93.11% in 5 min, 15 min, and 30 min predictions, respectively. These results outperform existing models, especially in long-term predictions. The findings underscore the model's high accuracy and effectiveness across varying prediction durations, marking a significant advancement in traffic flow prediction. This suggests promising avenues for future research and practical applications.
format Article
id doaj-art-63da166b30bf4f7583a33d7d8b0b08c0
institution DOAJ
issn 2095-6215
language English
publishDate 2024-06-01
publisher Tsinghua University Press
record_format Article
series Journal of Highway and Transportation Research and Development
spelling doaj-art-63da166b30bf4f7583a33d7d8b0b08c02025-08-20T02:47:50ZengTsinghua University PressJournal of Highway and Transportation Research and Development2095-62152024-06-01182677510.26599/HTRD.2024.9480015An Improved Spatio-Temporal Network Traffic Flow Prediction Method Based on Impedance MatrixWenhao Li0Yanyan Chen1Yuyan Pan2Yunchao Zhang3Beijing Key Laboratory of Traffic Engineering, Beijing University of Technology, Beijing 100124, ChinaBeijing Key Laboratory of Traffic Engineering, Beijing University of Technology, Beijing 100124, ChinaBeijing Key Laboratory of Traffic Engineering, Beijing University of Technology, Beijing 100124, ChinaBeijing Key Laboratory of Traffic Engineering, Beijing University of Technology, Beijing 100124, ChinaEffective traffic management and congestion reduction heavily rely on accurate traffic flow prediction. Existing prediction methods, such as Markov, ARIMA, STANN, GLSTM, and DCRNN models, often face challenges because they rely on fixed spatial relationships, leading to limited long-term prediction accuracy. To address these shortcomings, this study proposes the Impedance-Spatio-Temporal Topological Network (Impedance-STTN) prediction model. The Impedance-STTN model integrates K-medoids clustering for data analysis, generating a real-time impedance matrix from impedance functions, traffic big data, and real-time flow data. This approach captures dynamic node relationships within the spatio-temporal network, enhancing prediction accuracy. Experimental results demonstrate the superior predictive performance of the Impedance-STTN model, achieving accuracies of 94.79%, 93.78%, and 93.11% in 5 min, 15 min, and 30 min predictions, respectively. These results outperform existing models, especially in long-term predictions. The findings underscore the model's high accuracy and effectiveness across varying prediction durations, marking a significant advancement in traffic flow prediction. This suggests promising avenues for future research and practical applications.https://www.sciopen.com/article/10.26599/HTRD.2024.9480015traffic engineeringtraffic predictionspatio-temporal correlationreal time impedance matrixsttn network
spellingShingle Wenhao Li
Yanyan Chen
Yuyan Pan
Yunchao Zhang
An Improved Spatio-Temporal Network Traffic Flow Prediction Method Based on Impedance Matrix
Journal of Highway and Transportation Research and Development
traffic engineering
traffic prediction
spatio-temporal correlation
real time impedance matrix
sttn network
title An Improved Spatio-Temporal Network Traffic Flow Prediction Method Based on Impedance Matrix
title_full An Improved Spatio-Temporal Network Traffic Flow Prediction Method Based on Impedance Matrix
title_fullStr An Improved Spatio-Temporal Network Traffic Flow Prediction Method Based on Impedance Matrix
title_full_unstemmed An Improved Spatio-Temporal Network Traffic Flow Prediction Method Based on Impedance Matrix
title_short An Improved Spatio-Temporal Network Traffic Flow Prediction Method Based on Impedance Matrix
title_sort improved spatio temporal network traffic flow prediction method based on impedance matrix
topic traffic engineering
traffic prediction
spatio-temporal correlation
real time impedance matrix
sttn network
url https://www.sciopen.com/article/10.26599/HTRD.2024.9480015
work_keys_str_mv AT wenhaoli animprovedspatiotemporalnetworktrafficflowpredictionmethodbasedonimpedancematrix
AT yanyanchen animprovedspatiotemporalnetworktrafficflowpredictionmethodbasedonimpedancematrix
AT yuyanpan animprovedspatiotemporalnetworktrafficflowpredictionmethodbasedonimpedancematrix
AT yunchaozhang animprovedspatiotemporalnetworktrafficflowpredictionmethodbasedonimpedancematrix
AT wenhaoli improvedspatiotemporalnetworktrafficflowpredictionmethodbasedonimpedancematrix
AT yanyanchen improvedspatiotemporalnetworktrafficflowpredictionmethodbasedonimpedancematrix
AT yuyanpan improvedspatiotemporalnetworktrafficflowpredictionmethodbasedonimpedancematrix
AT yunchaozhang improvedspatiotemporalnetworktrafficflowpredictionmethodbasedonimpedancematrix