基于双参数寻优车联网交通流量指数平滑预测

Research on Smooth Forecast of Traffic Flow Index Based on Double Parameter Search in Vehicle of Network

随着我国汽车保有量持续大幅增加,交通拥堵、空气污染、能源浪费、时间延误、雾霾加重等问题日益严重。为了有效解决上述问题,对道路交通实行智能控制与管理的智能交通系统应运而生。以车流量这个道路交通拥堵重要的影响因素为研究对象,结合实际的短时交通流数据,在传统指数平滑法建模的基础上,针对其中的平滑系数和初值这两个关键参数的选取,提出了基于等步长双参数寻优的三次指数平滑改进算法。最后,依据实测的短时交通流量数据进行仿真实验,实验结果表明:改进的指数平滑模型较之于传统指数平滑模型在预测精度方面更具优势。

As China’s car ownership continues to increase substantially,and the problems of traffic congestion,air pollution,energy waste,time delay and haze aggravation are becoming more and more serious.In order to solve these problems effectively,intelligent traffic system construction with intelligent control and management of road traffic arises at the historic moment.And one of the hot topics of research is the integration of Internet of Things,big data and cloud computing.Based on the technology of Internet of vehicles,this paper studies how to predict short-term traffic flow in real time and accurately and effectively prevent traffic congestion.Based on the actual short-time traffic flow data,and the traditional exponential smoothing method,the index smoothing method is improved on the basis of the traditional exponential smoothing method.Then an improved exponential smoothing method is used to build a traffic flow prediction model based on exponential smoothing method.Finally,based on the measured short-term traffic flow data of a certain road section,the prediction model is simulated.The experimental results show that the prediction accuracy of the improved model is much better than that of the traditional exponential smoothing method.