Font Size: a A A

Intelligent Transportation Application Research Based On Stochastic Service Theory

Posted on:2019-04-25Degree:MasterType:Thesis
Country:ChinaCandidate:S LiFull Text:PDF
GTID:2322330566965940Subject:Computer Science and Technology
Abstract/Summary:PDF Full Text Request
In recent years,the problem of urban traffic congestion has become increasingly serious,the traditional fixed-time traffic light can not meet the increasing demand of the traffic,so the adaptive timing of traffic lights has become a research focus.The basis of adaptive timing is the real-time traffic retention,the traffic retention refers to the number of vehicles of a given length of road section and its junction.Accurate traffic retention prediction can provide support for the dynamic allocation of traffic signal,and it is an important content in the research of intelligent transportation.In this paper,a traffic retention prediction system is proposed,the research contents are as follows:(1)A traffic flow prediction based on combined model(TFPCM)is proposed,the model includes time series segmentation algorithm based on K-means clustering and Extreme Learning Machine(ELM)algorithm.The traffic flow can be predicted by using this model,which will pave the way for the subsequent prediction of traffic retention.Experiments have shown that this TFPCM model is more efficient and faster than other algorithms such as BP neural network.(2)The simulation program of the road system is designed with VISSIM software.The COM interface was used to input the traffic flow in real time,which make the simulation process closer to the actual operation status of traffic flow.The original evaluation data is provided for the follow-up prediction of traffic retention.(3)A prediction model of traffic retention based on stochastic service theory is proposed.The system model is abstracted on the basis of the physical model of the traffic road,and then a stochastic service model is established.and we work out thestochastic service model,get the calculation formula of the system retention,thus calculate the predicted traffic retention.After comparing with the actual value,the feasibility of the model for forecasting traffic retention was proved.(4)We analysis a large amount of experimental data,a deep summary is made on the research of the traffic retention prediction system,and the innovative points of this paper are introduced,and the areas need to be improved and the next development direction are pointed out.This paper verifies the traffic retention prediction system.Experimental results show that the traffic retention prediction system can predict the traffic retention accurately and effectively,and the calculation of the system is simple,it is also convenient for engineering practice.What is more,the system can provide data support for the the adaptive timing of traffic lights,and provides a theoretical basis for urban traffic guidance and control,the intelligent transportation is come true.
Keywords/Search Tags:intelligent transportation, traffic retention prediction, stochastic model, time series segmentation, extreme learning machine, TFPCM model
PDF Full Text Request
Related items