神经网络和遗传算法在动态路径诱导中的应用

针对智能交通路径诱导目前存在的实时性差和求解效率低的问题,提出了将神经网络与遗传算法结合的动态路径诱导方法,研究了基于神经网络的交通信息实时预测方法,构造了具有时变性的路阻矩阵,解决了传统静态路阻存在时变性差等的局限性问题;探讨了基于遗传算法的最优路径求解问题,提出了适用于路径优化的编码方式、适应度函数和遗传操作算子,解决了求解效率和求解质量的平衡问题。仿真实验表明,该方法满足路径诱导的准确性、实时性和快速性要求。     

基于改进遗传算法的路网路径优化方法

根据动态交通信息模型,用遗传算法求解最优路径问题,并根据编码的特点提出了一种新的迭代算子。文章后部分通过计算机仿真证明了算法的可行性。软件实现采用VC++平台。     

饱和路网中动态交通分配和控制一体化建模研究

对饱和路网中动态交通分配和交叉口信号控制的一体化建模进行了研究 .描述了一个双层规划问题 .上层以动态用户均衡为目标建立分配模型 ,下层以系统最优为目标进行信号设置 .考虑了饱和路段上的车辆排队行为和驾驶员路径选择行为 ,并在模型中加以描述 .最后将遗传算法与传统的非线性最优规划方法相结合求解了一体化模型     

基于量子进化算法求解动态交通分配模型

解决城市交通局部拥挤的最佳途径是进行路径引导,其核心理论是实时动态交通分配。针对这类模型变量多、维数大以及约束条件多等局限性,本文提出了一种以量子进化方法作为路网的交通均衡分配的主要优化方法,以整个交通网络中各条出行路径的总出行时间最小为优化目标的动态交通分配模型的求解方法。仿真实验结果证实了利用量子进化求解动态交通分配问题的有效性与合理性。     

基于并行遗传神经网络算法的动态路径选择方法

实时、高效的求解大规模路网中的最优路径是动态路径诱导领域的研究难点。针对基本遗传算法在计算大型网络的优化问题时表现出的求解效率低等缺点,在基本遗传算法中引入了子群体和迁移策略,提出了基于并行遗传算法的最优路径选择方法,设计了适用于路径优化的编码方式、适应度函数、遗传操作算子和迁移算子,并采用神经网络预测方法构造了实时动态的路阻矩阵。仿真试验表明:该方法的准确性、实时性和快速性优于基本遗传算法,并且大规模路网中求解效率和求解质量的平衡问题也得以解决。     

基于并行遗传神经网络算法的动态路径选择方法

实时、高效的求解大规模路网中的最优路径是动态路径诱导领域的研究难点.针对基本遗传算法在计算大型网络的优化问题时表现出的求解效率低等缺点,在基本遗传算法中引入了子群体和迁移策略,提出了基于并行遗传算法的最优路径选择方法,设计了适用于路径优化的编码方式、适应度函数、遗传操作算子和迁移算子,并采用神经网络预测方法构造了实时动态的路阻矩阵.仿真试验表明该方法的准确性、实时性和快速性优于基本遗传算法,并且大规模路网中求解效率和求解质量的平衡问题也得以解决.     

基于Stackelberg博弈的动态用户最优配流和信号控制

研究了动态用户最优配流与信号控制的组合问题.首先基于交通分配将交通流分配到合适的路网上由信号控制来适应这些交通流的思想,并由此建立了交通分配和信号控制的Stackelberg博弈模型,模型的上层是动态用户最优,下层是信号控制优化.然后,通过对模型离散化应用模拟退火算法进行求解.最后,对一个简单的交通网络进行仿真,仿真结果表明所提方法的有效性.     

城市交通最优路径规划仿真研究

研究城市交通最优路径规划问题,由于城市交通网复杂,增加了规划的难度,传统的最优路径规划算法没有考虑城市道路网络中的交通限制问题,更忽略了车辆在道路交叉口转向延误的时间,不符合城市交通的实际情况.为了解决上述问题.首先建立了一个城市路网交通模璎.然后运用线性规划方法建立最优路径规划问题的线性规划模型.最后采用桶排序算法对狄杰斯特拉算法进行优化,得到一个新的最优路径规划算法,对线性规划模型进行求解.仿真结果证明,利用算法搜索得到的最优路径更加符合实际的路网情况,为设计提供了理论依据.     

基于改进蚁群算法的物流运输最优路径优化模型构建

为在复杂交通环境中快速准确求解物流运输最优路径,本文基于改进蚁群算法构建了物流运输最优路径优化模型.通过仿真分析,结果表明相比遗传算法与传统蚁群算法,基于改进蚁群算法的物流运输最优路径长度均值明显较小,表明改进蚁群算法获得了相对更优的物流运输路径,加快了物流运输速度,减少了物流运输时间与成本,实际效益更为突出;且迭代次数明显较少,不仅加快了物流运输最优路径问题求解效率,还实现了大规模物流运输最优路径优化模型问题求解,实践应用范围广泛.     

高维多目标动态停车场选择及路径诱导研究

现有停车诱导系统中采用的停车场选择及路径诱导方法多局限于提供用户出行前多目标最优的停车场选择方案及路径诱导方案,无法实现用户行进过程中动态的多目标停车场及路径优化选择,此外由于现有多目标优化算法性能受限,无法快速获得真正高维多目标最优的决策方案.针对上述问题,提出一种综合用户出行前静态的和行进中动态的高维多目标停车场选择及路径诱导模型,并设计了高维多目标优化算法KS-MODE保证模型的高效求解.实验结果表明,KS-MODE在4～15目标优化问题上的收敛性能相比较于现有多种算法具有明显优势,基于KS-MODE的模型求解能够在城市交通网中实现出行前及行进中的五目标最优的动态停车场选择及路径诱导,证明了高维多目标优化算法是求解停车场选择及路径诱导的有效方法,能够提高现有停车诱导系统的诱导精度及智能化程度.     

Dynamic load balancing in IP-over-WDM optical burst switching networks

In this paper, we consider the problem of dynamic load balancing in wavelength division multiplexing (WDM)-based optical burst switching (OBS) networks. We propose a load balancing scheme based on adaptive alternate routing aimed at reducing burst loss. The key idea of adaptive alternate routing is to reduce network congestion by adaptively distributing the load between two pre-determined link-disjoint alternative paths based on the measurement of the impact of traffic load on each of them. We develop two alternative-path selection schemes to select link-disjoint alternative paths to be used by adaptive alternate routing. The path selection schemes differ in the way the cost of a path is defined and in the assumption made about the knowledge of the traffic demands. Through extensive simulation experiments for different traffic scenarios, we show that the proposed dynamic load balancing algorithm outperforms the shortest path routing and static alternate routing algorithms.     

基于道路风险评估的城市路网实时路径选择

为了缓解城市交通拥堵、避免交通事故的发生,城市路网的路径选择一直以来是一个热门的研究课题.随着边缘计算和车辆智能终端技术的发展,城市路网中的行驶车辆从自组织网络朝着车联网(Internet of vehicles,IoV)范式过渡,这使得车辆路径选择问题从基于静态历史交通数据的计算向实时交通信息计算转变.在城市路网路径选择问题上,众多学者的研究主要聚焦如何提高出行效率,减少出行时间等.然而这些研究并没有考虑所选路径是否存在风险等问题.基于以上问题,首次构造了一个基于边缘计算技术的道路风险实时评估模型(real-time road risk assessment model based on edge computing, R³A-EC),并提出基于该模型的城市路网实时路径选择方法(real-time route selection method based on risk assessment, R²S-RA). R3A-EC模型利用边缘计算技术的低延迟,高可靠性等特点对城市道路进行实时风险评估,并利用最小风险贝叶斯决策验证道路是否存在风险问...     

Hierarchical multiobjective routing in Multiprotocol Label Switching networks with two service classes: a heuristic solution

Modern multiservice network routing functionalities have to deal with multiple, heterogeneous and multifaceted Quality of Service (QoS) requirements. A heuristic approach devised to find "good" solutions to a hierarchical multiobjective alternative routing optimization problem in Multiprotocol Label Switching networks with two service classes (and different types of traffic flows in each class), namely QoS and Best Effort services, formulated within a hierarchical network-wide optimization framework, is presented. This heuristic solution is based on a bi-objective constrained shortest path model and is applied to a test network used in a benchmarking case study. An experimental study based on analytic and discrete event simulation results is presented, allowing for an assessment of the quality of results obtained with this new heuristic solution for various traffic matrices. A dynamic version of the routing method is formulated and its performance with the same case study network is analysed.     

A Hybrid Genetic and Ant Colony Algorithm for Finding the Shortest Path in Dynamic Traffic Networks

Solving the dynamic shortest path problem has become important in the development of intelligent transportation systems due to the increasing use of this technology in supplying accurate traffic information. This paper focuses on the problem of finding the dynamic shortest path from a single source to a destination in a given traffic network. The goal of our studies is to develop an algorithm to optimize the journey time for the traveler when traffic conditions are in a state of dynamic change. In this paper, the models of the dynamic traffic network and the dynamic shortest path were investigated. A novel dynamic shortest path algorithm based on hybridizing genetic and ant colony algorithms was developed, and some improvements in the algorithm were made according to the nature of the dynamic traffic network. The performance of the hybrid algorithm was demonstrated through an experiment on a real traffic network. The experimental results proved that the algorithm proposed in this paper could effectively find the optimum path in a dynamic traffic network. This algorithm may be useful for vehicle navigation in intelligent transportation systems.     

紧急事件的动态交通流模型及双向动态最短路诱导算法

针对城市快速路的交通紧急事件给出了宏观的动态交通流模型,在METANET模型的基础上考虑紧急事件所占用车道数、进出口匝道及诱导信息对模型的影响,同时针对交通紧急事件的及时有效处理,给出了一种双向动态的最短路径诱导算法,在此算法中,节点间的权值是随着高速路的路面状况及交通拥堵情况等变化的动态函数,故在紧急事件处理中从两个方向搜索最短路,其过程是动态的,实时的,为紧急事件的及时处理和有效的救援争取了时间。通过仿真对比,证明了此算法的可行性,有效性,同时证明了此算法的搜索效率也得到了较大提高。     

Decremental algorithm for adaptive routing incorporating traveler information

Routing in a stochastic and dynamic (time-dependent) network is a crucial transportation problem. A new variant of adaptive routing, which assumes perfect online information of continuous real-time link travel time, is proposed. Driver's speed profile is taken into consideration to realistically estimate travel times, which also involves the stochasticity of links in a dynamic network. An adaptive approach is suggested to tackle the continuous dynamic shortest path problem. A decremental algorithm is consequently developed to reduce optimization time. The impact of the proposed adaptive routing and the performance of the decremental approach are evaluated in static and dynamic networks under different traffic conditions. The proposed approach can be incorporated into vehicle navigation systems.     

动态交通网络中最优路径查找算法*

在真实交通网络中,可能出现某高速公路在某一时刻内通过的车辆过多,从而改变了该时刻道路的即时速度,这就需要对道路的交通流量进行监控。针对这一问题,通过建立交通网络的速度模式库,根据道路可达速度的变化更新速度模式。基于A*算法与速度模式库,提出针对动态交通网络的最短路径查询算法。采用真实数据集对算法进行测试,结果表明,应用该方法能够有效地解决在速度模式发生变化的情况下最优路径的查找,使交通网络中的最优路径查询更为准确有效。     

基于交通方向的较优路径选路算法

Dijkstra算法是计算最短路径的典型算法,它能得出最短路径的最优解,但因为遍历计算的节点很多,所以效率低下.针对此局限性,提出一种基于方向判别的较优路径选择算法.该算法利用交通网络的方向特性,能够快速收敛找到较优路径,提高选路算法的性能.引入偏差率和吻合率等概念来描述算法,对其设计与实现过程进行详细的阐述,并利用MATLAB进行仿真实验.实验结果表明该算法在性能上优于Dijkstra算法,尽管得出的路径不一定是最优路径,会存在偏差,然而这些偏差是可以容忍的,不会影响算法的价值.     

A Dynamic Road Incident Information Delivery Strategy to Reduce Urban Traffic Congestion

Advanced information and communication technologies can be used to facilitate traffic incident management. If an incident is detected and blocks a road link, in order to reduce the incident-induced traffic congestion, a dynamic strategy to deliver incident information to selected drivers and help them make detours in urban areas is proposed by this work. Time-dependent shortest path algorithms are used to generate a subnetwork where vehicles should receive such information. A simulation approach based on an extended cell transmission model is used to describe traffic flow in urban networks where path information and traffic flow at downstream road links are well modeled. Simulation results reveal the influences of some major parameters of an incident-induced congestion dissipation process such as the ratio of route-changing vehicles to the total vehicles, operation time interval of the proposed strategy, traffic density in the traffic network, and the scope of the area where traffic incident information is delivered. The results can be used to improve the state of the art in preventing urban road traffic congestion caused by incidents.      

基于离散动态规划的航班多级签派策略优化

飞行签派是航班运行控制的核心,为实现放行和动态控制策略的全局规划及定量评价,改变传统人工经验解读规章手册的定性技术手段,构造航班受签派策略影响下的二维状态转移路线;提出最短路径的离散动态递推规划数学模型,建立最小费用逆序递推的离散最优控制算法,运用数值计算方法得到表格形式的签派优化策略,解决了航班运行决策这类非线性、离散复合动态规划问题的定量评估和组合优化。最后,采用仿真实验测试算法的可行性和优化效果,实验结果表明,对比独立分阶段的遵照时间序列的运行方式,基于离散动态规划的航班多级签派策略贯穿于航班运行整个生命周期,实现全局优化。