A dynamic ensemble deep deterministic policy gradient recursive network for spatiotemporal traffic speed forecasting in an urban road network

doi:10.1016/j.dsp.2022.103643

	A dynamic ensemble deep deterministic policy gradient recursive network for spatiotemporal traffic speed forecasting in an urban road network
	Mi, Xiwei 1,5; Yu, Chengqing 2; Liu, Xinwei 4; Yan, Guangxi 3; Yu, Fuhao 1; Shang, Pan 1
	2022-09-01
发表期刊	DIGITAL SIGNAL PROCESSING
ISSN	1051-2004
卷号	129 页码:16
摘要	Traffic congestion is a difficult problem that restricts the construction of urbanization. Spatiotemporal traffic speed forecasting technologies can provide effective technical support for alleviating traffic congestion and ensuring vehicle travel safety. The ensemble learning algorithm is a hot topic in traffic speed modeling. In this field, previous ensemble learning methods mainly adopt the principle of static modeling, which limits the learning ability of the model to dynamic features. To solve this problem, in this paper, a new dynamic ensemble deep deterministic policy gradient recursive network is presented for traffic speed forecasting, which comprises three main modeling steps. In step I, the simple recursive network (SRU) and temporal convolution network (TCN) methods are used as the main predictors to build the traffic speed forecasting model. In step II, the multi-objective imperialist competitive algorithm (MOICA) integrates these neural networks by optimizing the weight coefficients and generating the Pareto solution set. In step III, the deep deterministic policy gradient (DDPG) method dynamically selects the Pareto optimal solution of the MOICA according to the changes in the traffic speed data. The MOICA and DDPG dynamically integrate the forecasting results from the SRU and TCN to obtain the final results. Based on the experimental analysis results, several conclusions can be given as follows: (a) the model presented in this paper can obtain accurate traffic speed forecasting results with MAPE values below 4% on all data sets. (b) the proposed model can achieve better results than thirteen alternative models and four proposed models from other researchers. (c) the proposed model can improve the prediction performance of traditional predictors by about 6%. (C) 2022 Elsevier Inc. All rights reserved.
关键词	Spatiotemporal traffic speed forecasting Deep deterministic policy gradient Simple recursive network Temporal convolution network
DOI	10.1016/j.dsp.2022.103643
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[52102471] ; National Natural Science Foundation of China[72001020] ; Beijing Natural Science Foundation[L201016] ; Fundamental Research Funds for the Central Universities (Science and technology leading talent team project)[2022JBXT008] ; National Key Research and Development Program of China[2018YFB1201402]
WOS研究方向	Engineering
WOS类目	Engineering, Electrical & Electronic
WOS记录号	WOS:000862260300014
出版者	ACADEMIC PRESS INC ELSEVIER SCIENCE
引用统计	被引频次：14[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/19811
专题	中国科学院计算技术研究所期刊论文
通讯作者	Shang, Pan
作者单位	1.Beijing Jiaotong Univ, Sch Traff & Transportat, Beijing 100044, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China 3.Cent South Univ, Sch Traff & Transportat Engn, Changsha 410075, Peoples R China 4.Beijing Jiaotong Univ, Sch Mech Elect & Control Engn, Beijing 10004, Peoples R China 5.Beijing Jiaotong Univ, Collaborat Innovat Ctr Railway Traff Safety, Beijing 10004, Peoples R China
推荐引用方式 GB/T 7714	Mi, Xiwei,Yu, Chengqing,Liu, Xinwei,et al. A dynamic ensemble deep deterministic policy gradient recursive network for spatiotemporal traffic speed forecasting in an urban road network[J]. DIGITAL SIGNAL PROCESSING,2022,129:16.
APA	Mi, Xiwei,Yu, Chengqing,Liu, Xinwei,Yan, Guangxi,Yu, Fuhao,&Shang, Pan.(2022).A dynamic ensemble deep deterministic policy gradient recursive network for spatiotemporal traffic speed forecasting in an urban road network.DIGITAL SIGNAL PROCESSING,129,16.
MLA	Mi, Xiwei,et al."A dynamic ensemble deep deterministic policy gradient recursive network for spatiotemporal traffic speed forecasting in an urban road network".DIGITAL SIGNAL PROCESSING 129(2022):16.