基于残差修正GM(1,1)模型的车流量预测

Traffic Flow Forecast Based on Residual Modification GM(1,1)Model

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。

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.