Integration of Signal Control and Transit Signal Priority Optimization in Coordinated Network Using Genetic Algorithms and Artificial Neural Networks
Integration of Signal Control and Transit Signal Priority Optimization in Coordinated Network Using Genetic Algorithms and Artificial Neural Networks
复制标题
DOI：
--
复制
发表时间：
2009
期刊：
影响因子：
--
通讯作者：
M. Ghanim;F. Dion;G. Abu-Lebdeh
中科院分区：
文献类型：
--
作者：
M. Ghanim;F. Dion;G. Abu-Lebdeh
许多公交机构目前正在考虑实施优先系统，为公交车提供临时绿灯延长和城市信号交叉口早期绿色召回。虽然许多研究已经评估了减少公交延误和负面交通影响的潜力，但这些研究大多集中在传统的固定时间交通信号控制系统中的实施。很少有人研究协调实时交通信号控制系统中公交信号优先(TSP)的整合问题。在这种情况下，一个特别的问题是，当考虑到服务站点停留时间的可变性时，预测过境移动的不确定性。利用遗传算法(GA)和人工神经网络(ANN)建模，开发了一种集交通信号配时优化和TSP控制于一体的实时交通信号控制器。遗传算法用于寻找接近最优的信号配时，而神经网络用于预测公交线路上的公交车出行。评价结果表明，与传统的有无TSP的固定时间控制以及基于遗传算法的无TSP实时控制方法相比，所提出的集成控制器能够减少换乘延误，提高调度依从性和服务可靠性，并有利于非换乘交通。
Many transit agencies are currently considering implementing priority systems providing buses with temporary green signal extensions and early green recalls at urban signalized intersections. While many studies have evaluated the potential for bus delay reductions and negative traffic impacts, most of these studies focused on implementations within traditional fixed-time traffic signal control systems. Only a few studies have addressed the problems of integrating transit signal priority (TSP) in coordinated real-time traffic signal control systems. A particular problem in this case is the uncertainty of predicting transit movements when considering the variability of dwell times at service stops. This study presents the development of a real-time traffic signal controller integrating traffic signal timing optimization and TSP control using a Genetic Algorithm (GA) and an Artificial Neural Networks (ANN) modeling. The GA is used to find near-optimal signal timings while the ANN is used to predict the travel of buses along transit routes. Evaluation results show that the proposed integrated controller can reduce transit delay, improve schedule adherence and service reliability, and benefit non-transit traffic compared to traditional fixed-time control with and without TSP, as well as a real-time GA-based control approach without TSP.