摘要
交通流量预测是智能交通系统发挥其应有效能的重要内容之一。在分析目前短时交通流预测相关研究的基础上,结合交通系统交通流量复杂性和非线性等特征,提出了一种基于分形插值的三次指数平滑模型短时交通流量预测模型。然后根据实测交通流量数据,对构建的预测模型进行了仿真实验和验证。验证结果表明,文中所构建的预测模型与常用的支持向量机和GM(1,1)交通流量预测算法相比,预测精度得到了大幅提高,其拟合精度平均相对误差为2. 3495%,预测的平均相对误差达到2. 363%。
Traffic flow prediction is one of the important contents of intelligent transportation system.Firstly,By analyzing the short term traffic flow forecasting,combined with the complexity and the nonlinearity of traffic flow,a short term traffic flow prediction model combined with fractal interpolation and three exponential smoothing model is proposed.Then,the prediction model is simulated and verified by the measured traffic flow data.The results show that the prediction accuracy of the proposed model is improved compared with the prediction accuracy of the algorithm for the common support vector machine and the GM (1,1) traffic flow.The average relative error of the fitting accuracy is 2.3495% and the average relative error of the prediction is 2.363%.
作者
高洪波
张登银
GAO Hongbo;ZHANG Dengyin(College of Intemet of Things,Nanjing University of Posts and Telecommunications,Nanjing 210003,China;College of Arts Media,Nantong Open University,Nantong 226006,China)
出处
《南京邮电大学学报（自然科学版）》
北大核心
2018年第6期63-67,共5页
Journal of Nanjing University of Posts and Telecommunications：Natural Science Edition
基金
国家自然科学基金(61571241)
江苏省高等学校自然科学研究(15KJA510002)资助项目
关键词
分形插值
指数平滑法
短时交通流量
预测
仿真
fractal interpolation
exponential smoothing
short-term traffic flow
prediction
simulation
