Unlock instant, AI-driven research and patent intelligence for your innovation.

A Short-term Traffic Flow Forecasting Method

A technology of short-term traffic flow and prediction method, which is applied in the field of short-term traffic flow prediction, can solve problems such as no consideration, and achieve the effect of avoiding defects, good prediction effect and high precision

Active Publication Date: 2019-12-27
HENAN POLYTECHNIC UNIV
View PDF3 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when the data fluctuates greatly, the reliability of the prediction results of the sub-model is not considered.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A Short-term Traffic Flow Forecasting Method
  • A Short-term Traffic Flow Forecasting Method
  • A Short-term Traffic Flow Forecasting Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0045] Gray scale prediction theory [11-12] Using limited data to estimate limited uncertain behavior is a method of data preprocessing, which can effectively weaken the volatility of data and reduce the randomness of data. It does not require the support of a large amount of historical data, nor does it need to consider various influencing factors. Look for patterns in time series of observations. Its essence is to accumulate the original sequence, then establish a first-order differential equation, and use an exponential curve to fit the data to predict the data at the next moment. Therefore, it can be used to reveal the changing trend of traffic flow and achieve the purpose of short-term traffic flow prediction.

[0046] The prediction algorithm of the gray algorithm sub-model is:

[0047] If there is a traffic flow sequence x, and there are Q ob...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to a short-time traffic flow prediction method. The prediction method is characterized by including the following steps: 1) predicting the traffic flow of the p + 1st time period by means of a gray algorithm and an ELM nerve network respectively; 2) calculating the standard deviation S of the traffic flows for the first few periods of the p + 1st time period and the error of submodels in the p time period, and obtaining the predicted weight of the two submodels in the next time period based on the error; and 3) if the standard deviation of the traffic flow rates for several time periods before the p period satisfies the relation Sp>S0, directly taking the predicted result of the ELM algorithm as the predicted value of the time, and if the standard deviation of the several time periods before the p-1st time period satisfies the relation Sp-1>S0, giving the submodels of a combined module a fixed weight to eliminate the influence of the gray algorithm.

Description

technical field [0001] The invention provides a short-term traffic flow prediction method. Background technique [0002] With the continuous development of the economy, people's demand for cars continues to increase, which makes the highway traffic flow continuously increase. The traffic problem has increasingly become a complex problem that plagues people's lives. Intelligent transportation is an effective way to solve complex traffic problems without changing the current road network. Timely traffic guidance and traffic control is the core content of intelligent transportation. Short-term traffic flow prediction is the key to realize traffic guidance and control, and it is also the basis of intelligent traffic management system. [0003] The following are prior art documents relevant to the application: [0004] [1] Han Chao, Song Su, Wang Chenghong. Real-time adaptive prediction of short-term traffic flow based on ARIMA model [J]. Journal of System Simulation, 2004,16...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G08G1/01G08G1/065G06Q10/04
CPCG06Q10/04G08G1/0125G08G1/0129G08G1/065
Inventor 钱伟车凯李冰锋黄凯征刘海波
Owner HENAN POLYTECHNIC UNIV