基于残差修正GM(1,1)模型的车流量预测

doi:10.11896/j.issn.1002-137X.2017.04.021

摘要/Abstract

摘要： 车流量预测是城市智能交通系统研究中的热难点问题之一,精确的车流量预测能有效地支持智能交通系统的发展,减少拥堵。同时车流量预测的精确度密切关系着居民的出行质量。然而车流量受诸多因素的不同程度的影响,具有一定程度的随机性、灰色性和不确定性,从城市交叉路口得到的车流量监控数据也具有一定程度的缺失和偏差,简单、准确且高效地预测车流量成为一个挑战。基于交叉路口采集到的车牌识别数据,通过对比经典GM(1,1)得到的预测值与真实值计算出残差,用残差去修正计算模型进而得到修正GM (1,1)模型,再用得到的修正模型迭代处理同一数据集,最后,数值稳定收敛且精度高于未修正模型的结果。

关键词: 车流量预测,GM(1,1)灰度模型,残差

Abstract: Traffic flow prediction has been one of the core problems in urban transport system.Accurate and efficient traffic prediction can effectively support the urban transportation planning, effectively reduce traffic congestion and the waste of resources and emissions.The accuracy of vehicle traffic forecast is also closely related to the residents’ travel quality.However,traffic is affected by many uncertain factors that has a certain degree of uncertainty,randomness and gray.The data from city intersection traffic monitors also has a certain degree of loss and deviation.Simplely,accurately and efficiently predicting traffic is a problem. Using the data from monitors,through the prediction value of GM (1,1) model comparing with real value to compute residual,using residual to modify computing model to get modified GM (1,1)model,multiple iterations are used for the same data set,and the final results are stable and superior to the classic GM (1,1) model.Experiments show that compared with the classic GM (1,1) model,the improved GM (1,1) model to get the predicted values is more close to the real value.With the complexity of the classical algorithm,the calculation accuracy is improved to some extent.

Key words: Traffic flow forecast,Grey GM(1,1),Residual

赵卓峰,杨宗润. 基于残差修正GM(1,1)模型的车流量预测[J]. 计算机科学, 2017, 44(4): 96-99. https://doi.org/10.11896/j.issn.1002-137X.2017.04.021

ZHAO Zhuo-feng and YANG Zong-run. Traffic Flow Forecast Based on Residual Modification GM(1,1) Model[J]. Computer Science, 2017, 44(4): 96-99. https://doi.org/10.11896/j.issn.1002-137X.2017.04.021

参考文献

[1] CHEN Y,XIAO X P.Research on short time traffic flow forecasting model based on fraction accumulation generation[D].Wuhan:Wuhan University of Technology,2014:8-9.(in Chinese) 陈野,肖新平.基于分数阶累加生成的短时交通流预测模型研究[D].武汉:武汉理工大学,2014:8-9.
[2] STEPHANEDES V J,MICHALOPOULOS P G,PLUM R A.Improved estimation of traffic flow for real time control[J].Transportation Research Record,1981,79(5):28-39.
[3] CHEN S Y,CHEN J S.Application of A Novel Grey Model to Traffic Flow Prediction[J].Journal of highway and transportation research and development,2004,21(2):80-83.(in Chinese) 陈淑燕,陈家胜.一种改进的灰色模型在交通量预测中的应用[J].公路交通科技,2004,21(2):80-83.
[4] SHEN G J,ZHU Y,QIAN X J,et al.Short-term traffic flowforecasting based on hybrid model[J].Journal of Nanjing University of Science and Technology,2014,38(2):246-251.(in Chinese) 沈国江,朱芸,钱晓杰,等.短时交通流组合模型预测[J].南京理工大学学报,2014,38(2):246-251.
[5] OKUTANI I,STEPHANEDES Y J.Dynamic prediction of tra-fic volume through Kalman filtering theory[J].Transportation Research.Part B:Methodological,1984,18(1):1-11.
[6] GUAN S,GAO J W,ZHANG B,et al.Traffic Flow Prediction Based on K-Means Clustering Algorithm and RBF Neural Network[J].Journal of Qingdao University(Engineering & Technology Edition),2014,29(2):20-23.(in Chinese) 管硕,高军伟,张彬,等.基于K-均值聚类算法RBF神经网络交通流预测[J].青岛大学学报(工程技术版),2014,29(2):20-23.
[7] 邵春福,熊志华.道路网短时交通需求预测理论、方法及应用[M].北京:清华大学出版社,2011:8-9
[8] YU R,WANG G X,ZHENG J Y,et al.Urban Road TrafficCondition Pattern Recognition Based on Support Vector Machine[J].Journal of Transportation Systems Engineering and Information Technology,2013,29(2):130-136.(in Chinese) 于荣,王国祥,郑继媛,等.基于支持向量机的城市道路交通状态模式识别研究[J].交通运输系统工程与信息,2013,29(2):130-136
[9] LEI S M,JIA X J,YU Z Y.Short term traffic flow forecastbased on gauss kernel function[J].Journal of MUC(Natural Sciences Edition),2013,3(3):82-87.(in Chinese)雷少梅,贾旭杰,于在洋.基于高斯核函数的短时交通流量预测[J].中央民族大学学报(自然科学版),2013,3(3):82-87.
[10] XIE Y,ZHAO K,SUN Y,et al.Gaussian Processes for Short-Term Traffic Volume Forecasting[J].Transportation Research Record:Journal of the Transportation Research Board,2010,2165(-1):69-78.
[11] YU B,WU S H,WANG M H,et al.K nearest neighbor short-term traffic flow forecasting model[J].Journal of Traffic and Transportation Engineering,2012,12(2):105-111.(in Chinese) 于滨,邬珊华,王明华,等.K-临近短时交通流预测模型[J].交通运输工程学报,2012,12(2):105-111.
[12] WILLIAMS B M,HOEL L A.Modeling and Forecasting Vehi-cular Traffic Flow as a Seasonal ARIMA Process:Theoretical Basis and Empirical Results[J].Journal of Transportation Engineering,2014,129(6):664-672.
[13] SUN S,YU G,ZHANG C.Short-term traffic flow forecastingusing Sampling Markov Chain method with incomplete data[C]∥Intelligent Vehicles Symposium,2004 IEEE.IEEE,2004:437-441.
[14] ZHANG S,ZHAO Z F,DING W L,et al.Urban Road Trip Time Measured Calculation Based on Map- Reduce[J].Compu-ter and Digital Engineering,2014,2(9):1542-1546.(in Chinese) 张帅,赵卓峰,丁维龙,等.基于MapReduce的城市道路旅行时间实测计算[J].计算机与数字工程,2014,2(9):1542-1546.
[15] 邓聚龙.灰预测与灰决策(修订版)[M].武汉:华中科技大学出版社,2002.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed