Traffic Flow-Big Data Forecasting Method Based on Spatial-Temporal Weight Correlation

doi:10.13209/j.0479-8023.2017.040

Abstract

Abstract:

A distributed incremental aggregation method combined with traffic flow data cleansing rules is proposed, and it can provide more accurate and reliable data for traffic flow forecast analysis. Through the correlation analysis of traffic flow in road network, the authors used the multi-allocation of turning rate in the intersection to build the spatial weight matrix, and improved the STARIMA traffic flow forecasting model. The experiment result proves that this method can meet the needs of traffic flow big-data forecasting in the efficiency and accuracy, and provide the basis for the traffic routing information.

Key words: traffic flow, big-data, distributed incremental, road network correlation, STARIMA

摘要：

将分布式增量大数据聚合方法与交通流数据清洗规则相结合, 可以为交通流预测分析提供更准确可靠的数据源。通过交通流在路网中的相关性分析, 使用多阶路口转弯率构建空间权重矩阵, 完成对STARIMA交通流预测模型的改进。实验结果表明, 该方法可以在工作效率及准确程度上满足交通流大数据预测的需求, 为交通诱导信息发布提供依据。

关键词: 交通流, 大数据, 分布式增量, 路网相关性, STARIMA

Xin LI, Qing LUO, Deyou MENG. Traffic Flow-Big Data Forecasting Method Based on Spatial-Temporal Weight Correlation[J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2017, 53(4): 775-782.

李欣, 罗庆, 孟德友. 基于时空权重相关性的交通流大数据预测方法[J]. 北京大学学报自然科学版, 2017, 53(4): 775-782.

Add to citation manager EndNote|Ris|BibTeX

URL: https://xbna.pku.edu.cn/EN/10.13209/j.0479-8023.2017.040

https://xbna.pku.edu.cn/EN/Y2017/V53/I4/775

Figures/Tables 9

References 29

[1]	李德仁, 马军, 邵振峰. 论时空大数据及其应用. 卫星应用, 2015(9):7-11
[2]	Bose J H, Andrzejak A, Hogqvist M. Beyond online aggregation: parallel and incremental data mining with online Map-Reduce // Proc of Workshop on Massive Data Analytics on the Cloud.New York: ACM, 2010: 1-6
[3]	Aghabozorgi S, Saybani M R, Wah T Y. Incremental clustering of time-series by fuzzy clustering.Journal of Information Science and Engineering, 2012,28(4):671-688
[4]	Laptev N, Zeng K, Zaniolo C. Very fast estimation for result and accuracy of big data analysis: the EARL system // Proc of ICDE. Piscataway. Brisbane: IEEE, 2013: 1296‒1299
[5]	Zhang S B, Han J Z, Liu Z Y, et al.Accelerating mapreduce with distributed memory cache // Proc of ICPADS. Piscataway. Shenzhen: IEEE, 2009: 472‒ 478
[6]	Stephanedes Y J, Michalopoulos P G.Improved estimation of traffic flow for real-time control // Transportation Research Record 795. Washington DC: Transportation Research Board, 1981: 28‒39
[7]	Okutani I, Stephanedes Y J. Dynamic prediction of traffic volume through Kalman filtering theory. Transportation Research Part B: Methodological, 1984,18(1):1-11
[8]	Ahmaed M S, Cook A R.Analysis of freeway traffic time-series data by using Box-Jenkins technique // Transportation Research Record 722. Washington DC: Transportation Research Board, 1979:1-9
[9]	Doughetry M S, Cobbett M R.Short-term inter-urban traffic forecasts using neural networks. International Journal of Forecasting,1997,13(1):21-31
[10]	Ledoux C. An urban traffic flow model integrating neural networks. Transportation Research Part C: Emerging Technologies, 1997,5(5):287-300
[11]	Yue Yang.Spatial-temporal dependency of traffic flow and its implications for short-term traffic forecasting [D]. Hong Kong: The University of Hong Kong, 2006
[12]	Kamarianakis Y, Prastacos P.Space-time modeling of traffic flow. Computers & Geosciences, 2005,31:119-133
[13]	Martin R L, Oeppen J E. The identification of regional forecasting models using space-time correlation functions.Trans Inst Brit Geogr, 1975,66:95-118
[14]	余碧莹, 邵春福. 基于时空模型的道路网交通状态预测 // 第四届中国智能交通年会论文集. 青岛, 2008:546-551
[15]	Lin Shulan, Huang Hongqiang, Zhu Daqi, et al.The application of space-time ARIMA model On traffic flow forecasting // Proceedings of the 8th International Conference on Machine Learning and Cybernetics..Baoding, 2009: 3408‒3412
[16]	Min Xinyu, Hu Jianming, Chen Qi, et al. Short-term traffic flow forecasting of urban network based on dynamic STARIMA model // Proceedings of the 12th International IEEE Conference on Intelligent Trans-portation Systems. St. Louis, MO, 2009: 461‒466
[17]	瞿莉. 基于动态交通流分配参数的网络交通状态建模与分析[D]. 北京: 清华大学, 2010
[18]	张和生, 张毅, 胡东成, 等. 区域交通状态分析的时空分层模型. 清华大学学报: 自然科学版, 2007,47(1):157-160
[19]	王晓原, 张敬磊. 交通流信息挖掘的非参数概率变点模型研究. 武汉理工大学学报: 交通科学与工程版, 2010,34(4):801-805
[20]	郭志懋, 周傲英.数据质量和数据清洗研究综述.软件学报,2002,13(11):2076-2082
[21]	张敬磊, 王晓原. 基于非线性组合模型的交通流预测方法. 计算机工程, 2010,36(5):202-205
[22]	王晓原, 张敬磊, 吴芳. 交通流数据清洗规则研究.计算机工程, 2011,37(20):191-193
[23]	Pfeifer P E, Deutsch S J.A three-stage iterative procedure for space-time modeling. Technometrics, 1980,22(1):35-47
[24]	Pfeifer P E, Deutsch S J..Identification and interpretation of first-order space-time ARMA models. Technometrics, 1980,22(3):397-408
[25]	Pfeifer P E, Deutsch S J.Variance of the sample- time autocorrelation function of contemporaneously correlated variables.SIAM Journal of Applied Mathe-matics,Series A, 1981,40(1):133-136
[26]	Deng Shuo, Hu Jianming, Wang Yin, et al.Urban road network modeling and real-time prediction based on house holder transformation and adjacent vector // Proceedings of the 6th International Symposium on Neural Networks. Berlin: Springer, 2009:899-908
[27]	Bezdek J C, Pal N R. Some new indexes of cluster validity.IEEE Trans Syst Man Cy, 1998,28:301-315
[28]	Kamarianakis Y, Prastacos P.Space-time modeling of traffic flow. Comput Geosci-UK, 2005,31:119-133
[29]	牛新征, 佘堃. 面向大规模数据的快速并行聚类划分算法研究. 计算机科学, 2012(1): 134-137

下游路段编号	对应上游路段编号
6	7, 10, 14
8	5, 10, 14
9	5, 7, 14
13	5, 7, 10

下游路段编号	对应上游路段编号
6	7, 10, 14
8	5, 10, 14
9	5, 7, 14
13	5, 7, 10

算法	t/s
算法	2万条数据	5万条数据	10万条数据	20万条数据	50万条数据	100万条数据
MPI	3.595	9.573	18.365	36.879	91.368	180.774
MapReduce	16.786	31.213	43.357	60.674	87.849	135.407

算法	t/s
算法	2万条数据	5万条数据	10万条数据	20万条数据	50万条数据	100万条数据
MPI	3.595	9.573	18.365	36.879	91.368	180.774
MapReduce	16.786	31.213	43.357	60.674	87.849	135.407

路段编号	Dynamic STARIMA	路网相关 STARIMA	路段编号	Dynamic STARIMA	路网相关 STARIMA	路段编号	Dynamic STARIMA	路网相关 STARIMA
1	8638.27	6643.68	22	3338.29	2839.48	43	3977.67	3058.83
2	7396.01	6032.39	23	6236.77	5064.66	44	4458.98	3847.45
3	6631.31	4983.57	24	7784.39	5338.54	45	8979.37	7432.82
4	8362.58	5986.44	25	2526.67	1438.33	46	8443.69	6234.73
5	2948.21	1863.49	26	3464.32	1974.34	47	2798.55	1846.49
6	4820.22	2799.35	27	8764.39	5890.43	48	3985.42	2275.45
7	9230.23	7390.32	28	6549.48	5438.93	49	7849.43	5893.37
8	7857.46	6074.45	29	12974.45	8865.29	50	6692.38	5624.78
9	15324.01	12984.61	30	13084.44	10474.63	51	6639.32	4542.43
10	11479.46	8753.05	31	5478.34	3740.35	52	5873.57	4147.57
11	3892.27	2775.73	32	4858.34	3275.39	53	3720.32	2475.54
12	4917.48	3295.48	33	7434.95	6578.36	54	3920.28	2143.27
13	3729.33	2903.57	34	7868.23	5920.49	55	2039.58	1343.47
14	3928.23	2638.57	35	6743.23	4839.33	56	3235.62	1634.57
15	4478.19	3902.29	36	7820.33	5923.67	57	4838.88	3822.44
16	6903.36	4632.84	37	8068.35	6488.38	58	5749.23	4727.28
17	10573.48	7296.23	38	7819.28	6367.35	59	6403.45	4884.74
18	9033.54	7018.83	39	3894.22	2057.75	60	6653.63	4954.54
19	4847.34	3892.33	40	4780.44	3628.65	61	7570.49	6343.45
20	3309.21	3087.88	41	7897.36	4929.38	62	8788.48	6932.43
21	5789.22	4274.49	42	8902.34	5563.37