当前位置>主页 > 期刊在线 > 信息技术 >

信息技术2020年4期

基于 Spark 框架的实时交通流量预测方法
章茂庭,杨楠,蒋顺英,郑永玲,白宇
(贵州民族大学 数据科学与信息工程学院,贵州 贵阳 550025)

摘  要:在数据科技时代,针对集中式挖掘平台下传统 LSTM 网络模型在处理移动轨迹大数据时存在的计算与存储问题,提出一种 Spark 框架下基于 LSTM 优化模型的实时交通流量预测方法,旨在于提高交通流量预测的精确性。实践结果表明,基于真实的出租车 GPS 轨迹大数据,Spark 框架下的 LSTM 优化模型可以实时准确地预测交通流量。


关键词:实时交通流量预测;Spark;LSTM;GPS 轨迹大数据;参数调整



中图分类号:TP202+.2;U491.1+23         文献标识码:A         文章编号:2096-4706(2020)04-0001-08


  Real-time Traffic Flow Prediction Method Based on Spark Framework

ZHANG Maoting,YANG Nan,JIANG Shunying,ZHENG Yongling,BAI Yu

(School of Data Science and Information Engineering,Guizhou Minzu University,Guiyang 550025,China)

Abstract:In the era of data science and technology,the traditional LSTM network model in the centralized mining platform has the problems of computing and storage when dealing with the big data of mobile trajectory,this paper proposes a real-time traffic flow prediction method based on the LSTM optimization model under the Spark framework,which aims to the improvements of accuracy of traffic flow prediction. The experiment results of a case study demonstrate that with real-world taxi GPS trajectory big data,the proposed LSTM optimization model based on the Spark framework can accurately predict traffic flow in real time. 

Keywords:real-term traffic flow prediction;Spark;LSTM;GPS track big data;parameter adjustment


参考文献:

[1] 杜小勇,陈跃国,范举,等 . 数据整理——大数据治理的关键技术 [J]. 大数据,2019,5(3):13-22.

[2] ZHANG J,WANG F Y,WANG K,et al. Data-Driven Intelligent Transportation Systems:A Survey [J]. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,2011,12(4):1624-1639.

[3] JIA Y H,WU J P,XU M. Traffic Flow Prediction with Rainfall Impact Using a Deep Learning Method [J]. Journal of Advanced Transportation,2017:1-10.

[4] 陆化普,孙智源,屈闻聪 . 大数据及其在城市智能交通系统中的应用综述 [J]. 交通运输系统工程与信息,2015,15(5):45-52.

[5] 陈聪,张国惠,马晓磊,等 . 利用大数据挖掘和知识发现技术辅助智慧城市发展 [J]. 大数据,2016,2(3):39-48.

[6] QIAO S L,SUN R C,FAN G P,et al. Short-term traffic flow forecast based on parallel long short-term memory neural network  [C]. Proceedings of 2017 IEEE 8th International Conference on Software Engineering and Service Science,IEEE BEIJING SECTION,2017:253-257.

[7] ZHAO Z,CHEN W,WU X,et al. LSTM network:a deep learning approach for short-term traffic forecast [J]. Intelligent Transport Systems Iet,2017,11(2):68-75.

[8] OKUTANI I,STEPHANEDES Y J. Dynamic prediction of traffic volume through Kalman filtering theory [J]. Transportation Research Part B Methodological,1984,18(1):1-11.

[9] ALGHAMDI T,ELGAZZAR K,BAYOUMI M,et al. Forecasting traffic congestion using ARIMA modeling [C]. 201915th International Wireless Communications and Mobile Computing Conference (IWCMC),2019:1227-1232.

[10] XIA D W,WANG B F,LI H Q,et al. A distributed spatialtemporal weighted model on MapReduce for short-term traffic flow forecasting [J]. Neurocomputing,2016,179(Feb.29):246-263.

[11] LUO X L,LI D Y,YANG Y,et al. Spatiotemporal Traffic Flow Prediction with KNN and LSTM [J]. Journal of Advanced Transportation,2019,(PT.1):537-546.

[12] LIU B Y,CHENG J R,CAI K Q,et al. Singular point probability improve LSTM network performance for long-term traffic flow prediction [C]// National Conference of Theoretical Computer Science,2017:328-340.

[13] LI Z S,XIONG G,CHEN Y Y,et al. A hybrid deep learning approach with GCN and LSTM for traffic flow prediction [C]//2019 IEEE Intelligent Transportation Systems Conference (ITSC). IEEE2019:1929-1933.

[14] 刘钊,杜威,闫冬梅,等 . 基于 K 近邻算法和支持向量回归组合的短时交通流预测 [J]. 公路交通科技,2017,34(5):122-128+158.

[15] 陈小波,刘祥,韦中杰,等 . 基于 GA-LSSVR 模型的路网短时交通流预测研究 [J]. 交通运输系统工程与信息,2017,17(1):60-66+81.

[16] WANG J Y,XU X F,WANG F S,et al. A deep predictionarchitecture for traffic flow with precipitation information [C]//International Conference on Sensing and Imaging. Springer,Cham,2018:329-338.

[17] MA X L,TAO Z M,WANG Y H,et al. Long shortterm memory neural network for traffic speed prediction using remotemicrowave sensor data [J]. Transportation Research Part C:Emerging Technologies,2015,54:187-197.

[18] JEONG Y S,BYON Y J,CASTRO-NETO M M,et al.Supervised Weighting-Online Learning Algorithm for Short-Term Traffic Flow Prediction [J]. IEEE Transactions on Intelligent Transportation Systems,2013,14(4):1700-1707.

[19] FU R,ZHANG Z,LI L. Using LSTM and GRU neural network methods for traffic flow prediction [C]// Youth Academic Conference of Chinese Association of Automation. IEEE,2016:324-328.

[20] CHEN Y Y,LV Y S,LI Z J,et al. Long short-term memory model for traffic congestion prediction with online open data [C]// 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC). IEEE,2016:132-137.

[21] AGAFONOV A,YUMAGANOV A. Spatial-temporal K Nearest Neighbors model on MapReduce for traffic flow prediction [C]//International Conference on Intelligent Data Engineering and Automated Learning. Springer,Cham,2018:253-260.

[22] LUO C,HUANG C,CAO J D,et al. Short-term traffic flow prediction based on least square support vector machine with hybrid optimization algorithm [J]. Neural Processing Letters,2019:1-18.

[23] CHAI Y C,HUANG D R,ZHAO L. A Short-term traffic flow prediction method based on wavelet analysis and neural network [C]//2016 Chinese Control and Decision Conference (CCDC).IEEE,2016:7030-1034.


作者简介:

章茂庭(1994-),女,汉族,贵州三穗人,就读于数据科学与信息工程学院,统计学研究生,研究方向:海量数据统计与分析;

杨楠(1997-),女,汉族,贵州盘县人,就读于数据科学与信息工程学院,统计学研究生,研究方向:海量数据统计与分析;

蒋顺英(1996-),女,汉族,贵州兴义人,就读于数据科学与信息工程学院,统计学研究生,研究方向:海量数据统计与分析;

郑永玲(1995-),女,汉族,贵州毕节人,就读于数据科学与信息工程学院,统计学研究生,研究方向:海量数据统计与分析;

白宇(1994-),女,汉族,贵州仁怀人,就读于数据科学与信息工程学院,统计学研究生,研究方向:海量数据统计与分析。