北大中文核心期刊
中国科学引文数据库（CSCD）来源期刊
中国科技核心期刊
入选数学领域高质量科技期刊
Scopus
EBSCO 

运筹学学报 ›› 2015, Vol. 19 ›› Issue (3): 71-77.doi: 10.15960/j.cnki.issn.1007-6093.2015.03.009

• 运筹学 • 上一篇    下一篇

基于类神经网络的城市交通信号区域优化算法

黄佳倩1, 洪振杰1, 范劲松1,*   

  1. 1.  温州大学数学与信息科学学院，浙江温州, 325035
  • 收稿日期:2015-05-04 出版日期:2015-09-15 发布日期:2015-09-15
  • 通讯作者: 范劲松 fjs@wzu.edu.cn

An optimized urban traffic signal field control algorithm based on pseudo neural network

HUANG Jiaqian1, HONG Zhenjie1, FAN Jinsong1,*   

  1. 1.  College of Mathematics and Information Science, Wenzhou University, Wenzhou 325035, Zhejiang, China
  • Received:2015-05-04 Online:2015-09-15 Published:2015-09-15

PDF

580

被引次数

1

摘要：

提出了一种可并行处理的交通信号配时区域优化模型和相应算法. 算法从局部枚举最优方案出发, 在枚举计算每个交叉口信号灯方案的罚分时, 在真实罚分的基础上叠加虚拟导向罚分. 虚拟导向罚分通过动态通行权重来计算. 将枚举法和虚拟导向罚分相结合, 使得算法具有空间和时间上的全局优化特性. 在道路处于饱和或过饱和状态时, 该算法相对于传统的单点定时或单点感应等交通信号配时方案具有明显的优化效果.

关键词: 神经网络, 信号配时优化, 动态通行权重, 并行计算

Abstract:

We propose an optimization model and its corresponding parallel algorithm for optimized signal-planning. Based on a local enumeration method, the algorithm adds a virtual guiding penalty, which is derived from the traffic weight. This makes the algorithm has a global spatial and temporal optimized property. In the situation of saturated or over-saturated traffic status, this algorithm outperforms the traditional single-point intersection control method.

Key words: neural network, signal timing optimization, dynamictraffic weight, parallel algorithm