城市交通流量预测模型的研究  

Research on Urban Traffic Flow Forecasting Model

作　　者：李劲松[1] 易明俊 LI Jinsong;YI Mingjun(Department of Science and Technology, Traffic Management Bureau, Wuhan Public Security Bureau, Wuhan 430030, China;Traffic Brigade, Jiang’an District, Wuhan Public Security Bureau, Wuhan 430019, China)

机构地区：[1]武汉市公安局交通管理局科技处,湖北武汉430030 [2]武汉市公安局江岸区交通大队,湖北武汉430019

出　　处：《微型电脑应用》2020年第9期92-96,共5页Microcomputer Applications

摘　　要：城市交通流量预测是具有社会价值的重要课题之一。由于城市交通流量预测涉及到一个复杂的非线性数据模式,因此精确预测的难度较大。为此,提出将支持向量回归模型(SVR)和连续蚁群优化算法(ACO)相结合对城市短期交通流量进行预测的思路。仿真结果表明,与常见的季节自回归滑动平均时间序列模型的预测方法相比,该模型能得到更准确的预测结果。Urban traffic flow forecasting is one of the important topics of social value.Because urban traffic flow prediction involves a complex nonlinear data model,accurate prediction is difficult.To this end,this paper proposes a combination of support vector regression model(SVR)and continuous ant colony optimization algorithm(ACO)to predict urban short-term traffic flow.The simulation results show that the model can obtain more accurate prediction results than the prediction method of the common seasonal autoregressive moving average time series model.

关 键 词：交通流量预测 支持向量回归 连续蚁群优化算法 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]