| 88 | 0 | 16 |
| 下载次数 | 被引频次 | 阅读次数 |
高速服务区吞吐量预测是提升运行效率和服务满意度的重要手段，传统的吞吐量预测任务主要基于时间序列预测算法，利用同一观测点的历史信息，通过统计或深度学习等方法预测未来数据。但在真实场景中，高速服务区流量存在空间关联效应和突发性变化效应等，而序列预测模型既忽略了相关服务区之间的影响，也无法适应流量突变的情况。为此，该文提出一种融合重力模型再分配的序列预测算法(Gravity Model Redistribution, GMAAN),GMAAN可在现有时间序列预测方法的基础上，使用重力模型将高速道路上的车流量在服务区之间进行再次分配。在参数设定上，通过元学习快速定位系数，有效解决了传统试算法和最小二乘法的效率问题。在浙江省高速服务区吞吐量的真实数据集上进行对比，结果表明模型效果优于现有时间序列预测模型，在MAPE指标上降低了5百分点以上。
Abstract：Throughput prediction of high-speed service area is an important means to improve operation efficiency and service satisfaction. Traditional throughput prediction is based on time series prediction model, using historical information of the same observation point, and predicting future data through statistical or deep learning methods. In the real scene, there are spatial correlation effects and sudden change effects in the traffic of high-speed service area. Therefore, such models ignore the influence between service areas and cannot adapt to the sudden change of traffic. For this reason, a Gravity Model Redistribution(GMAAN) is proposed. Based on other time series prediction methods, GMAAN uses the gravity model to redistribute the traffic flow on the high-speed road. Due to the low efficiency of the traditional calculation coefficient method and the least square method, the parameters are quickly located by the meta-learning method. The results show that the GMAAN model is better than the SOTA time series prediction method, and the MAPE index is reduced by more than 5 percentage points.
[1] WILLIAMS B M,HOEL L A.Modeling and forecasting vehicular traffic flow as a seasonal ARIMA process:theoretical basis and empirical results[J].Journal of Transportation Engineering,2003,129(6):664-672.
[2] XU D,WANG Y,JIA L,et al.Real-time road traffic state prediction based on ARIMA and Kalman filter[J].Frontiers of Information Technology & Electronic Engineering,2017,18(2):287-302.
[3] TANG J,CHEN X,HU Z,et al.Traffic flow prediction based on combination of support vector machine and data denoising schemes[J].Physica A:Statistical Mechanics and Its Applications,2019,534:120642.
[4] YANG L,YANG Q,LI Y,et al.K-Nearest neighbor model based short-term traffic flow prediction method[C]//2019 18th international symposium on distributed computing and applications for business engineering and science (DCABES).Xuzhou:IEEE,2019:27-30.
[5] SU Z,LIU Q,LU J,et al.Short-time traffic state forecasting using adaptive neighborhood selection based on expansion strategy[J].IEEE Access,2018,6:48210-48223.
[6] YU H,JI N,REN Y,et al.A special event-based K-nearest neighbor model for short-term traffic state prediction[J].IEEE Access,2019,7:81717-81729.
[7] HUANG W,SONG G,HONG H,et al.Deep architecture for traffic flow prediction:deep belief networks with multitask learning[J].IEEE Transactions on Intelligent Transportation Systems,2014,15(5):2191-2201.
[8] FU R,ZHANG Z,LI L.Using LSTM and GRU neural network methods for traffic flow prediction[C]//2016 31st youth academic annual conference of Chinese association of automation (YAC).Wuhan:IEEE,2016:324-328.
[9] ZHAO W,GAO Y,JI T,et al.Deep temporal convolutional networks for short-term traffic flow forecasting[J].IEEE Access,2019,7:114496-114507.
[10] YANG D,LI S,PENG Z,et al.MF-CNN:traffic flow prediction using convolutional neural network and multi-features fusion[J].IEICE Transactions on Information and Systems,2019,102(8):1526-1536.
[11] ZHAO L,SONG Y,DENG M,et al.Temporal graph convolutional network for urban traffic flow prediction method[J].arXiv:1811.05320,2018.
[12] ZHAO L,SONG Y,ZHANG C,et al.T-gcn:a temporal graph convolutional network for traffic prediction[J].IEEE Transactions on Intelligent Transportation Systems,2019,21(9):3848-3858.
[13] HAN X,GONG S.LST-GCN:long short-term memory embedded graph convolution network for traffic flow forecasting[J].Electronics,2022,11(14):2230.
[14] WANG Y,JING C,XU S,et al.Attention based spatiotemporal graph attention networks for traffic flow forecasting[J].Information Sciences,2022,607:869-883.
[15] 贾百强，徐延军，周涛.一种融合ST-GCN算法的高速公路节假日流量预测模型[J].上海船舶运输科学研究所学报，2022,45(5):58-65.
[16] ZHOU H,ZHANG S,PENG J,et al.Informer:beyond efficient transformer for long sequence time-series forecasting[C]//Proceedings of the AAAI conference on artificial intelligence.[s.l.]:AAAI,2021:11106-11115.
[17] WU H,HU T,LIU Y,et al.Timesnet:temporal 2d-variation modeling for general time series analysis[J].arXiv:2210.02186,2022.
[18] WANG S,WU H,SHI X,et al.Timemixer:decomposable multiscale mixing for time series forecasting[J].arXiv:2405.14616,2024.
[19] Transportation Research Board Committee on Highway Capacity and Quality of Service.Highway capacity manual[M].Washington:National Academy of Sciences,2000:21-5-21-8.
基本信息:
DOI：10.20165/j.cnki.ISSN1673-629X.2025.0225
中图分类号:U495;TP18
引用信息:
[1]陈虚竹,徐烽,丁剑超,等.融合重力模型再分配的服务区流量预测改进模型[J].计算机技术与发展,2026,36(02):180-187.DOI:10.20165/j.cnki.ISSN1673-629X.2025.0225.
基金信息:
科技创新2030——“新一代人工智能”重大项目(2022ZD0119100); 浙江省自然科学基金(LMS25F020012)
2025-09-23
2025-09-23
2025-09-23