隐马尔可夫模型的道路拥堵时间预测

doi:10.3778/j.issn.1002-8331.2012-0363

摘要/Abstract

摘要： 道路车辆拥堵问题导致交通事故增加，降低了居民的出行效率，长时间的道路拥堵更是加重了环境污染，造成国家经济损失等诸多问题。为缓解城市道路交通的拥堵问题，提高出行效率，基于隐马尔可夫模型，针对已有道路拥堵时间数据进行采集与建模，并对该隐马尔可夫模型进行训练，通过算法计算与分析，预测未来一段时间的道路拥堵情况，为人们的出行提供拥堵时间预测，而后提出不同时段通过道路用时最短的最优路径。对韦尔奇算法进行改进，在原算法基础上增加考虑前[n]时刻状态。利用改进型韦尔奇算法，使得训练集参数更精确，达到预测精度更高的目的。实验结果表明，预测数据结果与真实数据相比，误差不超过3%，该模型预测结果具有较高准确性。

关键词: 拥堵时间预测, 隐马尔可夫模型, 改进型韦尔奇算法, 最优路径

Abstract: The problem of road vehicle congestion leads to the increase of traffic accidents and reduces the travel efficiency of residents. Long-term road congestion aggravates environmental pollution and causes many problems such as national economic losses. In order to alleviate the congestion problem of urban road traffic and improve travel efficiency, based on the hidden Markov model, this paper collects and models the existing road congestion time data, trains the hidden Markov model, predicts the road congestion time in the future through algorithm calculation and analysis, and provides congestion time prediction for people’s travel, Then, the shortest optimal path through the road in different periods is proposed. The innovation of this paper is to improve Welch algorithm and add the state of the first [n] moments on the original basis. The improved Welch algorithm is used to make the parameters of the training set more accurate and achieve the purpose of higher prediction accuracy. The experimental results show that the error between the predicted data and the real data is no more than 3%, and the prediction result of the model has high accuracy.

Key words: congestion time prediction, hidden Markov model, improved Welch algorithm, optimal path

张绪冰, 谢雨飞. 隐马尔可夫模型的道路拥堵时间预测[J]. 计算机工程与应用, 2022, 58(16): 312-318.

ZHANG Xubing, XIE Yufei. Road Congestion Time Prediction Based on Hidden Markov Model[J]. Computer Engineering and Applications, 2022, 58(16): 312-318.

参考文献

[1] 钱双洋，陈喆，刘原序.基于改进贝叶斯算法的云服务可靠性预测方法研究[J].计算机应用与软件，2017，34（11）：34-38.
QIAN S Y，CHEN Z，LIU Y X，et al.Cloud service reliability prediction method based on improved Bayes[J].Computer Applications and Software，2017，34（11）：34-38.
[2] 白伟华，张传斌，张塽旖，等.基于异常值识别卡尔曼滤波器的短期交通流预测[J].计算机应用研究，2021，38（3）：817-821.
BAI W H，ZHANG C B，ZHANG S Y，et al.Outlier-identified Kalman filter for short-term traffic flow forecasting[J].Application Research of Computers，2021，38（3）：817-821.
[3] 杨文忠，张志豪，吾守尔·斯拉木，等.基于时间序列关系的GBRT交通事故预测模型[J].电子科技大学学报，2020，49（4）：615-621.
YANG W Z，ZHANG Z H，WUSHOUER S，et al.GBRT traffic accident prediction model based on time series relationship[J].Journal of University of Electronic Science and Technology of China，2020，49（4）：615-621.
[4] PATRA A K.Adaptive Kalman filtering model predictive controller design for stabilizing and trajectory tracking of inverted pendulum[J].Journal of the Institution of Engineers（India）：Series B，2020，101：677-688.
[5] 周晓，唐宇舟，刘强.基于卡尔曼滤波的道路平均速度预测模型研究[J].浙江工业大学学报，2020，48（4）：392-396.
ZHOU X，TANG Y Z，LIU Q.Research on road average speed prediction model based on Kalman filter[J].Journal of Zhejiang University of Technology，2020，48（4）：392-396.
[6] 韦凌翔，陈红，王永岗，等.基于RVM和ARIMA的短时交通流量预测方法研究[J].武汉理工大学学报（交通科学与工程版），2017，41（2）：349-354.
WEI L X，CHEN H，WANG Y G，et al.Study on the methods of short-term traffic flow forecasting based on RVM and ARIMA[J].Journal of Wuhan University of Technology（Transportation Science & Engineering），2017，41（2）：349-354.
[7] 于东海.短时交通流预测问题的研究[D].济南：山东大学，2017.
YU D H.Research on short-term traffic flow forecasting[D].Jinan：Shandong University，2017.
[8] 史国刚.连续交通流状态的离散特性分析与短时预测[D].南京：东南大学，2016.
SHI G G.Heteroscedasticity analysis and short term forecasting for continuum traffic flow conditions[D].Nanjing：Southeast University，2016.
[9] 胡枫.基于马尔可夫模型的短时交通流预测研究[D].南京：南京邮电大学，2013.
HU F.Short term traffic volume prediction based on Markov model[D].Nanjing：Nanjing University，2013.
[10] 赵庶旭，伍宏伟，刘昌荣.基于隐马尔可夫模型的最优交通路径模式识别[J].测试科学与仪器，2020，11（4）：351-357.
ZHAO Z X，WU H W，LIU C R.Pattern recognition of optimal traffic path based on HMM[J].Journal of Measurement Science and Instrumentation，2020，11（4）：351-357.
[11] BON A T，ISAH N.Hidden Markov model and forward-backward algorithm in crude oil price forecasting[J].IOP Conference Series：Materials Science and Engineering，2016，160：012067.
[12] STEENECK D，ENG-LARSSON F.The Baum-Welch algorithm with limiting distribution constraints[J].Operations Research Letters，2018，46（6）：563-567.
[13] JOSHI J C，KUMAR T，SRIVASTAVA S.Optimisation of hidden Markov model using Baum-Welch algorithm for prediction of maximum and minimum temperature over Indian Himalaya[J].Journal of Earth System Science，2017，126：3.
[14] 刘琳娜，蒋珉，柴干.基于RTMS的高速公路事件检测系统设计[J].计算机技术与发展，2011，21（4）：219-222.
LIU L N，JIANG M，CHAI G.Design of highway incident detection system based on RTMS[J].Computer Technology and Development，2011，21（4）：219-222.
[15] 赵树平.高速公路隧道拥堵成因及疏解方法研究[D].成都：西南交通大学，2019.
ZHAO S P.Research on congestion cause and dissolution method of expressway tunnle[D].Chengdu：Southwest Jiaotong University，2019.