Dynamic programming—neural network real-time traffic adaptive signal control algorithm

被引：0

作者：

Dušan Teodorović

Vijay Varadarajan

Jovan Popović

Mohan Raj Chinnaswamy

Sharath Ramaraj

机构：

[1] Virginia Polytechnic Institute and State University,Department of Civil and Environmental Engineering

[2] University of Belgrade,Faculty of Transport and Traffic Engineering

[3] PB Farradyne,Faculty of Transport and Traffic Engineering

[4] University of Belgrade,School of Industrial Engineering and Management

[5] Oklahoma State University,Computer Science Department

[6] Virginia Polytechnic Institute and State University,undefined

来源：

Annals of Operations Research | 2006年 / 143卷

关键词：

Real time traffic adaptive control; Neural networks; Dynamic programming;

D O I：

暂无

中图分类号：

学科分类号：

摘要：

In this paper, an “intelligent” isolated intersection control system was developed. The developed “intelligent” system makes “real time” decisions as to whether to extend (and how much) current green time. The model developed is based on the combination of the dynamic programming and neural networks. Many tests show that the outcome (the extension of the green time) of the proposed neural network is nearly equal to the best solution. Practically negligible CPU times were achieved, and were thus absolutely acceptable for the “real time” application of the developed algorithm.

引用

页码：123 / 131

页数：8