基于延迟时空依赖的非平稳时间序列交通流量预测模型

李小龙; 李曦; 刘洋; 李柄廷; 易畅言; 曾宁俊

doi:10.12263/DZXB.20250591

您当前的位置：

首页 >

文章列表页 >

基于延迟时空依赖的非平稳时间序列交通流量预测模型

学术论文 | 更新时间：2026-02-10

- 基于延迟时空依赖的非平稳时间序列交通流量预测模型
- Non-Stationary Time Series Traffic Flow Forecasting Model Based on Delayed Spatio-Temporal Dependencies
- 电子学报 2025年53卷第11期页码：4035-4050
- 作者机构：
  
  1.湖南工商大学计算机学院，湖南长沙 410205
  2.湘江实验室，湖南长沙 410205
  3.南京航空航天大学计算机科学与技术学院，江苏南京 211106
- 作者简介：
  
  [ "李小龙男，1981年6月出生于湖南省常德市.现为湖南工商大学计算机学院教授、博士生导师.主要研究方向为智慧交通、大模型、物联网等.E-mail: lxl@hutb.edu.cn" ]
  [ "李曦女，2000年11月出生于湖南省沅江市.湖南工商大学计算机学院硕士.主要研究方向为深度学习、数据分析等.E-mail: lmz1191652939@163.com" ]
  [ "刘洋女，1981年7月出生于湖南省常德市.现为湖南工商大学计算机学院助理研究员、博士.主要研究方向为深度学习、时空网络、知识图谱等.E-mail: 4889329@qq.com" ]
  [ "李柄廷男，1999年8月出生于湖南省长沙市.现为湖南工商大学计算机学院硕士生.主要研究方向为图神经网络、并行图着色等.E-mail: 437138609@qq.com" ]
  [ "易畅言男，1989年10月出生于浙江省绍兴市.现为南京航空航天大学计算机科学与技术学院教授.主要研究方向为随机优化、博弈论、激励机制、排队调度和人工智能等.中国电子学会会员编号：E190186644M.E-mail: changyan.yi@nuaa.edu.cn" ]
  [ "曾宁俊男，1994年12月出生于湖南省益阳市.现为湖南工商大学计算机学院讲师.主要研究方向为复杂非线性系统建模、控制与优化等.E-mail: 3149@hutb.edu.cn" ]
- 基金信息：
  
  湘江实验室重大项目(23XJ01001;22XJ01001);启元实验室创新基金(2022-JCJQ-LA-001-088);湖南省重点研发计划(2024JK2007);广西科技重大项目(2024AA15007)
- DOI：10.12263/DZXB.20250591
  中图分类号： TP311.1
- 收稿：2025-07-03，
  
  录用：2025-11-03，
  
  纸质出版：2025-11-25
- 稿件说明：
移动端阅览
李小龙, 李曦, 刘洋, 等. 基于延迟时空依赖的非平稳时间序列交通流量预测模型[J]. 电子学报, 2025, 53(11): 4035-4050.

LI Xiao-long, LI Xi, LIU Yang, et al. Non-Stationary Time Series Traffic Flow Forecasting Model Based on Delayed Spatio-Temporal Dependencies[J]. Acta Electronica Sinica, 2025, 53(11): 4035-4050.
李小龙, 李曦, 刘洋, 等. 基于延迟时空依赖的非平稳时间序列交通流量预测模型[J]. 电子学报, 2025, 53(11): 4035-4050. DOI：10.12263/DZXB.20250591

LI Xiao-long, LI Xi, LIU Yang, et al. Non-Stationary Time Series Traffic Flow Forecasting Model Based on Delayed Spatio-Temporal Dependencies[J]. Acta Electronica Sinica, 2025, 53(11): 4035-4050. DOI：10.12263/DZXB.20250591

摘要

建立精准的交通流量预测模型，对于优化交通系统管理、缓解城市交通拥堵、提升路网运行效率具有至关重要的作用.然而，实际交通流呈现出显著的非平稳特性与复杂的时空依赖关系，尤其是由突发事件、早晚高峰、节假日等引起的流量分布偏移，以及交通拥堵在路网中传播的延迟效应，给传统预测方法带来了严峻挑战.现有模型大多基于平稳性假设或采用静态时空建模方式，难以有效捕捉交通数据中的动态演化规律与异质性延迟依赖，导致预测精度受限、工程适用性不足.针对上述问题，本文提出一种基于延迟时空依赖的非平稳时间序列交通流量预测模型（Non-Stationary time series Forecasting Model，NSFM），旨在从频域和空域双重角度深入刻画交通流的动态演变机制.该模型首先利用傅里叶变换将非平稳时间序列分解为时变组分与时不变组分，分别刻画局部动态波动与全局稳态趋势，并通过正交性证明确保两类成分的独立性，为后续差异化建模奠定理论基础.在此基础上，模型进一步构建带有时延特征提取机制的特征融合模块，结合逐点卷积与位置编码，将交通流量、空间邻接关系、时间周期信息与延迟传播特征进行深度融合，从而精准捕捉站点间交通状态的时空演化与滞后响应规律.为建模离散站点间的空间自相关结构，本文引入Moran算子构建函数对函数回归预测框架，通过基函数展开与正交化处理，实现连续函数空间与离散观测站点之间的一致性映射，有效量化区域间的空间依赖强度，提升模型在复杂路网中的预测鲁棒性.为验证NSFM模型的有效性与泛化能力，我们在四个真实世界交通流量数据集（PEMS03、PEMS04、PEMS07、PEMS08）上进行了系统实验，实验表明，NSFM在多个评估指标上均显著优于现有主流模型，其中平均绝对百分比误差（MAPE）相较于SOTA模型，分别降低了7.48%、9.86%、3.20%、1.73%，展现出在非平稳场景下更优的预测精度与稳定性.

Abstract

Building accurate traffic flow prediction models is crucial for optimizing traffic system management

alleviating urban congestion

and enhancing road network operational efficiency. However

real-world traffic flow exhibits significant non-stationary characteristics and complex spatio-temporal dependencies. In particular

the distribution shifts caused by unexpected events

rush hours

and holidays

coupled with the delayed propagation of traffic congestion across the network

pose severe challenges to traditional forecasting methods. Most existing models

relying on stationary assumptions or static spatio-temporal modeling

struggle to effectively capture the dynamic evolution patterns and heterogeneous delayed dependencies within traffic data

leading to limited prediction accuracy and insufficient practical applicability. To address these limitations

this paper proposes a non-stationary time series traffic flow forecasting model based on delayed spatio-temporal dependencies (NSFM)

designed to deeply characterize the dynamic evolution mechanisms of traffic flow from both frequency and spatial domains. The model first employs Fourier Transform to decompose the non-stationary time series into time-varying and time-invariant components

capturing local dynamic fluctuations and global steady-state trends respectively

with orthogonality proven to ensure the independence between the two components

laying a theoretical foundation for subsequent differentiated modeling. Furthermore

the model constructs a feature fusion module with a delay feature extraction mechanism

integrating traffic flow

spatial adjacency relationships

temporal periodic information

and delay propagation features through pointwise convolution and positional encoding

thereby accurately capturing the spatio-temporal evolution and lagged response patterns of traffic states between stations. To model the spatial autocorrelation structure among discrete stations

this paper introduces the Moran operator to build a function-on-function regression prediction framework. Through basis function expansion and orthogonalization processing

a consistent mapping between the continuous function space and discrete observation stations is achieved

effectively quantifying the spatial dependency strength between regions and enhancing the model’s prediction robustness in complex road networks. To validate the effectiveness and generalization capability of the NSFM model

systematic experiments are conducted on four real-world traffic flow datasets (PEMS03

PEMS04

PEMS07

PEMS08). Experimental results demonstrate that NSFM significantly outperforms existing mainstream models across multiple evaluation metrics. Specifically

the mean absolute percentage error (MAPE) is reduced by 7.48%

9.86%

3.20%

and 1.73% respectively compared to SOTA models

demonstrating superior prediction accuracy and stability in non-stationary scenarios.

关键词

Keywords

references

ZHANG J P , WANG F Y , WANG K F , et al . Data-driven intelligent transportation systems: A survey [J ] . IEEE Transactions on Intelligent Transportation Systems , 2011 , 12 ( 4 ): 1624 - 1639 .

LIU R P , SHIN S Y . A review of traffic flow prediction methods in intelligent transportation system construction [J ] . Applied Sciences , 2025 , 15 ( 7 ): 3866 .

邓攀 , 刘俊廷 , 王晓 , 等 . STCTN: 一种基于时域偏倚校正与空域因果传递的时空因果表示学习方法 [J ] . 计算机学报 , 2023 , 46 ( 12 ): 2535 - 2550 .

DENG P , LIU J T , WANG X , et al . STCTN: A spatio-temporal causal representation learning method based on temporal bias adjustment and spatial causal transition [J ] . Chinese Journal of Computers , 2023 , 46 ( 12 ): 2535 - 2550 . (in Chinese)

唐文杰 , 肖一磊 , 孔祥宇 , 等 . CycleLLH: 一种基于周期性整合的新型网络流量预测模型 [J ] . 计算机学报 , 2024 , 47 ( 12 ): 2867 - 2888 .

TANG W J , XIAO Y L , KONG X Y , et al . CycleLLH: A new network traffic prediction model based on cycle integration [J ] . Chinese Journal of Computers , 2024 , 47 ( 12 ): 2867 - 2888 . (in Chinese)

黄昕 , 毛政元 . 基于时空多图卷积网络的网约车乘客需求预测 [J ] . 地球信息科学学报 , 2023 , 25 ( 2 ): 311 - 323 .

HUANG X , MAO Z Y . Prediction of passenger demand for online car-hailing based on spatio-temporal multi-graph convolution network [J ] . Journal of Geo-Information Science , 2023 , 25 ( 2 ): 311 - 323 . (in Chinese)

LAI Q , CHEN P . LEISN: A long explicit-implicit spatio-temporal network for traffic flow forecasting [J ] . Expert Systems with Applications , 2024 , 245 : 123139 .

GENG Z L , XU J , WU R S , et al . STGAFormer: Spatial-temporal gated attention transformer based graph neural network for traffic flow forecasting [J ] . Information Fusion , 2024 , 105 : 102228 .

PU B , LIU J S , KANG Y , et al . MVSTT: A multiview spatial-temporal transformer network for traffic-flow forecasting [J ] . IEEE Transactions on Cybernetics , 2024 , 54 ( 3 ): 1582 - 1595 .

XIAO J L , LONG B C . A multi-channel spatial-temporal transformer model for traffic flow forecasting [J ] . Information Sciences , 2024 , 671 : 120648 .

QIAN W Z , ZHAO Y , ZHANG D L , et al . Towards a unified understanding of uncertainty quantification in traffic flow forecasting [J ] . IEEE Transactions on Knowledge and Data Engineering , 2024 , 36 ( 5 ): 2239 - 2256 .

LIU X Y , LI X , FIUMARA G , et al . Link prediction approach combined graph neural network with capsule network [J ] . Expert Systems with Applications , 2023 , 212 : 118737 .

BOX G E P , JENKINS G M , REINSEL G C , et al . Time Series Analysis: Forecasting and Control [M ] . 5th Ed . Hoboken : John Wiley & Sons , 2015 .

QIAN Y R , CAI Q , PAN Y W , et al . Boosting diffusion models with moving average sampling in frequency domain [C ] // 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2024 : 8911 - 8920 .

YANG H M , PAN Z S , TAO Q , et al . Online learning for vector autoregressive moving-average time series prediction [J ] . Neurocomputing , 2018 , 315 : 9 - 17 .

LONG L F , LIU Q , PENG H , et al . Multivariate time series forecasting method based on nonlinear spiking neural P systems and non-subsampled shearlet transform [J ] . Neural Networks , 2022 , 152 : 300 - 310 .

TRAN D T , IOSIFIDIS A , KANNIAINEN J , et al . Temporal attention-augmented bilinear network for financial time-series data analysis [J ] . IEEE Transactions on Neural Networks and Learning Systems , 2019 , 30 ( 5 ): 1407 - 1418 .

XUE Z W , ZHANG Y , CHENG C , et al . Remaining useful life prediction of lithium-ion batteries with adaptive unscented Kalman filter and optimized support vector regression [J ] . Neurocomputing , 2020 , 376 : 95 - 102 .

BILLINGS S A , HONG X . Dual-orthogonal radial basis function networks for nonlinear time series prediction [J ] . Neural Networks , 1998 , 11 ( 3 ): 479 - 493 .

乔少杰 , 吴凌淳 , 韩楠 , 等 . 情景感知驱动的移动对象多模式轨迹预测技术综述 [J ] . 软件学报 , 2023 , 34 ( 1 ): 312 - 333 .

QIAO S J , WU L C , HAN N , et al . Multiple-motion-pattern trajectory prediction of moving objects with context awareness: A survey [J ] . Journal of Software , 2023 , 34 ( 1 ): 312 - 333 . (in Chinese)

ZHENG H F , LIN F , FENG X X , et al . A hybrid deep learning model with attention-based conv-LSTM networks for short-term traffic flow prediction [J ] . IEEE Transactions on Intelligent Transportation Systems , 2021 , 22 ( 11 ): 6910 - 6920 .

SHI X M , QI H , SHEN Y M , et al . A spatial-temporal attention approach for traffic prediction [J ] . IEEE Transactions on Intelligent Transportation Systems , 2021 , 22 ( 8 ): 4909 - 4918 .

MÉNDEZ M , MERAYO M G , NÚÑEZ M . Long-term traffic flow forecasting using a hybrid CNN-BiLSTM model [J ] . Engineering Applications of Artificial Intelligence , 2023 , 121 : 106041 .

GUO L B , WANG W Q , CHEN Z , et al . Newton-Cotes graph neural networks: On the time evolution of dynamic systems [EB/OL ] . ( 2023-10-20 )[ 2025-10-10 ] . https://arXiv.org/abs/2305.14642 https://arXiv.org/abs/2305.14642 .

XU M X , DAI W R , LIU C M , et al . Spatial-temporal transformer networks for traffic flow forecasting [EB/OL ] . ( 2023-03-29 )[ 2025-10-10 ] . https://arXiv.org/abs/2001.02908 https://arXiv.org/abs/2001.02908 .

WANG X , ZHOU T , WEN Q S , et al . CARD: Channel aligned robust blend transformer for time series forecasting [EB/OL ] . ( 2024-02-16 )[ 2025-10-10 ] . https://arxiv.org/abs/2305.12095 https://arxiv.org/abs/2305.12095 .

ZHAO K , ZHANG L . Causality-inspired spatial-temporal explanations for dynamic graph neural networks [C ] // 12th International Conference on Learning Representations (ICLR 2024) . Appleton : ICLR , 2024 : 1 - 13 .

YADAV H , SCHAEFER M , ZHAO K , et al . CASPFormer: Trajectory prediction from BEV images with deformable attention [C ] // Pattern Recognition . Cham : Springer , 2025 : 420 - 434 .

BAI L , YAO L N , LI C , et al . Adaptive graph convolutional recurrent network for traffic forecasting [C ] // Proceedings of the 34th International Conference on Neural Information Processing Systems . New York : ACM , 2020 : 17804 - 17815 .

LI F X , FENG J , YAN H , et al . Dynamic graph convolutional recurrent network for traffic prediction: Benchmark and solution [J ] . ACM Transactions on Knowledge Discovery from Data , 2023 , 17 ( 1 ): 1 - 21 .

BAI J D , ZHU J W , SONG Y J , et al . A3T-GCN: Attention temporal graph convolutional network for traffic forecasting [J ] . ISPRS International Journal of Geo-Information , 2021 , 10 ( 7 ): 485 .

LONG B C , ZHU W , XIAO J L . ST-RetNet: A long-term spatial-temporal traffic flow prediction method [EB/OL ] . ( 2024-07-13 )[ 2025-10-10 ] . https://arxiv.org/abs/2407.11074 https://arxiv.org/abs/2407.11074 .

ZHAO Y , DENG P , LIU J T , et al . Causal conditional hidden Markov model for multimodal traffic prediction [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2023 , 37 ( 4 ): 4929 - 4936 .

ZHOU Z , SHOJAFAR M , ABAWAJY J , et al . ECMS: An edge intelligent energy efficient model in mobile edge computing [J ] . IEEE Transactions on Green Communications and Networking , 2022 , 6 ( 1 ): 238 - 247 .

DAS S , DAS S K . A probabilistic link prediction model in time-varying social networks [C ] // 2017 IEEE International Conference on Communications . Piscataway : IEEE , 2017 : 1 - 6 .

BHATKAR S , GOSAVI P , SHELKE V , et al . Link prediction using GraphSAGE [C ] // 2023 International Conference on Advanced Computing Technologies and Applications . Piscataway : IEEE , 2024 : 1 - 5 .

SONG C , LIN Y F , GUO S N , et al . Spatial-temporal synchronous graph convolutional networks: A new framework for spatial-temporal network data forecasting [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2020 , 34 ( 1 ): 914 - 921 .

WU Z H , PAN S R , LONG G D , et al . Graph WaveNet for deep spatial-temporal graph modeling [EB/OL ] . ( 2019-05-31 )[ 2025-10-01 ] . https://arxiv.org/abs/1906.00121 https://arxiv.org/abs/1906.00121 .

BAI L , YAO L N , KANHERE S S , et al . STG2Seq: Spatial-temporal graph to sequence model for multi-step passenger demand forecasting [EB/OL ] . ( 2019-05-24 )[ 2025-10-10 ] . https://arxiv.org/abs/1905.10069 https://arxiv.org/abs/1905.10069 .

GUO S N , LIN Y F , FENG N , et al . Attention based spatial-temporal graph convolutional networks for traffic flow forecasting [C ] // Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence and Thirty-First Innovative Applications of Artificial Intelligence Conference and Ninth AAAI Symposium on Educational Advances in Artificial Intelligence . New York : ACM , 2019 : 922 - 929 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据