Urban traffic signal control system based on traffic flow prediction

Abstract

The invention discloses an urban traffic signal control system based on traffic flow prediction, which comprises a data center, a prediction module and an optimization module, wherein the data centerwhich is used for storing the neural network training of a data center and a prediction module and the prediction of traffic data at a next time interval; the data center adds the original real-time traffic data into the historical traffic data before the real-time traffic data is transmitted each time, and then updates the real-time traffic data; the prediction module is used for carrying out short-term traffic flow prediction, for a multi-intersection road section, the to-be-predicted road section is i, assuming that the current moment is in a time interval k, the to-be-predicted amount is the traffic flow of the next time interval, and the prediction basis is the known road section i and the past traffic flow of all the upstream or downstream road sections adjacent to the known road section i; and the optimization module is used for evaluating the congestion degree of the city according to the signal lamp timing scheme in the road and the prediction data output by the prediction module. According to the method, the traffic jam condition of the next time period is obtained in advance, and the signal lamp timing scheme with the minimum jam at the next moment is obtained.

Description

Technical field[0001]The invention relates to the field of traffic signal control traffic flow prediction, and mainly relates to an urban traffic signal control system based on traffic flow prediction.[0002]technical background[0003]Traffic signal control is an important part of urban intelligent transportation system. According to the mode of operation, traffic signal controllers can be divided into two categories: timing signal controllers and adaptive signal controllers. Since the cycle length and green signal ratio of the former controller are fixed, and the latter can be adaptively adjusted, the control effect of the adaptive signal controller is usually better. In recent years, artificial intelligence has provided new ways to solve this problem. For example, some researchers have proposed using fuzzy theory to design signal control schemes (X. Cheng and Z. Yang: Intelligent traffic signal control approach based on fuzzy-genetic algorithm. 2008 Fifth International Conference on...

AI Technical Summary

Problems solved by technology

The third category of forecasting models is based on modern computational intelligence methods, such as neural networks, fuzzy control, etc. These forecasting models do not consider the potential dynamic system or clear physical meaning in a strict sense, but pay more attention to the fitting of actual traffic flow phenomena Effect

[0006] Although various traffic flow forecasting techniques have been developed and achieved good predictive performance, these studies are separate from the research on traffic signal control

That is, existing research either focuses on traffic single-shot optimization or traffic flow prediction, but few works combine these two techniques

Images