基于组合预测模型的短时交通流预测

Short-Term Traffic Flow Prediction Based on Combination of Predictive Models

在现代智能交通系统中,短时交通流预测是实现先进的交通控制和交通诱导的关键技术之一.为了提高短时交通流预测的准确性,本文提出了一种基于组合预测模型的短时交通流预测方法.一方面,根据当前的交通流数据来动态调整其对未来预测的影响;另一方面,通过对历史交通流数据的时空特性分析,利用数据挖掘领域的相关知识寻求与当前交通流特性最为相似的历史曲线,并以其为基础来获得预测值的匹配值;然后,将二者获得的信息进行融合,采用多种不同的组合方式来实现短时交通流预测.以厦门市莲花路口断面的交通流量为例,通过对仿真图像和数据的分析,得出各种组合方法的预测平均绝对相对误差均小于10%,能够较好地满足交通诱导系统的需求.

In modern intelligent transportation systems, short-term traffic flow forecasting is one of the key technologies to achieve a real-time-traffic control and traffic guidance. In order to improve the precision of the short-term traffic flow forecasting, a short-term traffic flow prediction method is proposed based on the combination forecasting model. The future projections are dynamically adjusted according to the current traffic flow data in the first part. Meanwhile, through the analysis of spatial and temporal characteristics of historical traffic flow data, the historical curve similar to the current traffic flow characteristics is sought in another part to find the data that is matching to the predicted value. The information obtained by the both can be organically combinated in different ways to achieve the short-term traffic flow forecasting. Taking the traffic flow of Xiamen Lotus junction cross-section as an example, is the paper demonstrates that the average absolute relative deviations of the methods are all less than 10%, which is able to meet the requirements of the traffic guidance system （GIS）.