基于马尔可夫模型的交叉口两难区自适应控制

发布时间：2018-01-14 09:17

本文关键词：基于马尔可夫模型的交叉口两难区自适应控制　出处：《同济大学学报(自然科学版)》2016年09期 　论文类型：期刊论文

【摘要】：提出一种基于马尔可夫模型的信控交叉口两难区自适应控制方法.根据实时监测的两难区内车辆数据,采用马尔可夫模型主动预测陷入两难区内车辆数的概率分布,提出采用基于n近邻的状态转移矩阵的更新框架,并综合考虑相位时长,建立相位延长和切换时两难区内当量车辆数的计算模型,进而以相位切换的风险概率为准则,采用即时决策的交通控制自适应调整相位时长.以广州市某交叉口进行VISSIM仿真实验,在不同强度的交通条件下,验证提出方法的效用并进行参数敏感性分析.仿真结果表明经过模型参数校准后,提出的控制方法在有效减少陷入两难区内的车辆数的同时,可减小交叉口的平均延误.
[Abstract]:This paper presents an adaptive control method based on Markov model for the dilemmas of signal-controlled intersections, which is based on the real-time monitoring of vehicle data in the dilemmas. The Markov model is used to predict the probability distribution of the number of vehicles in the dilemma area. An update framework based on the n-nearest neighbor state transfer matrix is proposed and the phase duration is considered comprehensively. The calculation model of the number of equivalent vehicles in the dilemmas of phase prolongation and handover is established, and the risk probability of phase switching is taken as the criterion. The real-time traffic control is used to adjust the phase time. The VISSIM simulation experiment is carried out at a intersection in Guangzhou under different intensity traffic conditions. The simulation results show that the proposed control method can effectively reduce the number of vehicles in a dilemma after the model parameters are calibrated. It can reduce the average delay of intersection.
【作者单位】：同济大学道路与交通工程教育部重点实验室;
【基金】：国家“八六三”高技术研究发展计划(2012AA112307)
【分类号】：U491.54
【正文快照】： 城市信号控制交叉口的交通安全形势严峻.据NASS统计,全球发生在交叉口的事故约占事故总数的25%[1],而在2004年我国发生在交叉口的交通事故中,由交通信号灯引起的事故超过一万多件[2].交通信号配时方案的安全及合理设置,是信控交叉口交通安全保障的关键.目前,大多数交通控制系

【参考文献】