Real-Time Traffic Flow Forecasting via A Novel Method Combining Periodic-Trend Decomposition
Accurate and timely traffic flow forecasting is a critical task of the intelligent transportation system (ITS). The predicted results offer the necessary information to support the decisions of administrators and travelers. To investigate trend and periodic characteristics of traffic flow and develo...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-07-01
|
Series: | Sustainability |
Subjects: | |
Online Access: | https://www.mdpi.com/2071-1050/12/15/5891 |
id |
doaj-429d044ea8874baaa8dca1d79e63577d |
---|---|
record_format |
Article |
spelling |
doaj-429d044ea8874baaa8dca1d79e63577d2020-11-25T03:44:45ZengMDPI AGSustainability2071-10502020-07-01125891589110.3390/su12155891Real-Time Traffic Flow Forecasting via A Novel Method Combining Periodic-Trend DecompositionWei Zhou0Wei Wang1Xuedong Hua2Yi Zhang3School of Transportation, Southeast University, Nanjing 211189, ChinaSchool of Transportation, Southeast University, Nanjing 211189, ChinaSchool of Transportation, Southeast University, Nanjing 211189, ChinaSchool of Transportation, Southeast University, Nanjing 211189, ChinaAccurate and timely traffic flow forecasting is a critical task of the intelligent transportation system (ITS). The predicted results offer the necessary information to support the decisions of administrators and travelers. To investigate trend and periodic characteristics of traffic flow and develop a more accurate prediction, a novel method combining periodic-trend decomposition (PTD) is proposed in this paper. This hybrid method is based on the principle of “decomposition first and forecasting last”. The well-designed PTD approach can decompose the original traffic flow into three components, including trend, periodicity, and remainder. The periodicity is a strict period function and predicted by cycling, while the trend and remainder are predicted by modelling. To demonstrate the universal applicability of the hybrid method, four prevalent models are separately combined with PTD to establish hybrid models. Traffic volume data are collected from the Minnesota Department of Transportation (Mn/DOT) and used to conduct experiments. Empirical results show that the mean absolute error (MAE), mean absolute percentage error (MAPE), and mean square error (MSE) of hybrid models are averagely reduced by 17%, 17%, and 29% more than individual models, respectively. In addition, the hybrid method is robust for a multi-step prediction. These findings indicate that the proposed method combining PTD is promising for traffic flow forecasting.https://www.mdpi.com/2071-1050/12/15/5891intelligent transportation systemtraffic flow forecastingtraffic flow decompositiontime series decomposition approachhybrid prediction method |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Wei Zhou Wei Wang Xuedong Hua Yi Zhang |
spellingShingle |
Wei Zhou Wei Wang Xuedong Hua Yi Zhang Real-Time Traffic Flow Forecasting via A Novel Method Combining Periodic-Trend Decomposition Sustainability intelligent transportation system traffic flow forecasting traffic flow decomposition time series decomposition approach hybrid prediction method |
author_facet |
Wei Zhou Wei Wang Xuedong Hua Yi Zhang |
author_sort |
Wei Zhou |
title |
Real-Time Traffic Flow Forecasting via A Novel Method Combining Periodic-Trend Decomposition |
title_short |
Real-Time Traffic Flow Forecasting via A Novel Method Combining Periodic-Trend Decomposition |
title_full |
Real-Time Traffic Flow Forecasting via A Novel Method Combining Periodic-Trend Decomposition |
title_fullStr |
Real-Time Traffic Flow Forecasting via A Novel Method Combining Periodic-Trend Decomposition |
title_full_unstemmed |
Real-Time Traffic Flow Forecasting via A Novel Method Combining Periodic-Trend Decomposition |
title_sort |
real-time traffic flow forecasting via a novel method combining periodic-trend decomposition |
publisher |
MDPI AG |
series |
Sustainability |
issn |
2071-1050 |
publishDate |
2020-07-01 |
description |
Accurate and timely traffic flow forecasting is a critical task of the intelligent transportation system (ITS). The predicted results offer the necessary information to support the decisions of administrators and travelers. To investigate trend and periodic characteristics of traffic flow and develop a more accurate prediction, a novel method combining periodic-trend decomposition (PTD) is proposed in this paper. This hybrid method is based on the principle of “decomposition first and forecasting last”. The well-designed PTD approach can decompose the original traffic flow into three components, including trend, periodicity, and remainder. The periodicity is a strict period function and predicted by cycling, while the trend and remainder are predicted by modelling. To demonstrate the universal applicability of the hybrid method, four prevalent models are separately combined with PTD to establish hybrid models. Traffic volume data are collected from the Minnesota Department of Transportation (Mn/DOT) and used to conduct experiments. Empirical results show that the mean absolute error (MAE), mean absolute percentage error (MAPE), and mean square error (MSE) of hybrid models are averagely reduced by 17%, 17%, and 29% more than individual models, respectively. In addition, the hybrid method is robust for a multi-step prediction. These findings indicate that the proposed method combining PTD is promising for traffic flow forecasting. |
topic |
intelligent transportation system traffic flow forecasting traffic flow decomposition time series decomposition approach hybrid prediction method |
url |
https://www.mdpi.com/2071-1050/12/15/5891 |
work_keys_str_mv |
AT weizhou realtimetrafficflowforecastingviaanovelmethodcombiningperiodictrenddecomposition AT weiwang realtimetrafficflowforecastingviaanovelmethodcombiningperiodictrenddecomposition AT xuedonghua realtimetrafficflowforecastingviaanovelmethodcombiningperiodictrenddecomposition AT yizhang realtimetrafficflowforecastingviaanovelmethodcombiningperiodictrenddecomposition |
_version_ |
1724512928120438784 |