Transit network design by genetic algorithm with elitism

The transit network design problem is concerned with the finding of a set of routes with corresponding schedules for a public transport system. This problem belongs to the class of NP-Hard problem because of the vast search space and multiple constraints whose optimal solution is really difficult to find out. The paper develops a Population based model for the transit network design problem. While designing the transit network, we give preference to maximize the number of satisfied passengers, to minimize the total number of transfers, and to minimize the total travel time of all served passengers. Our approach to the transit network design problem is based on the Genetic Algorithm (GA) optimization. The Genetic Algorithm is similar to evolution strategy which iterates through fitness assessment, selection and breeding, and population reassembly. In this paper, we will show two different experimental results performed on known benchmark problems. We clearly show that results obtained by Genetic Algorithm with increasing population is better than so far best technique which is really difficult for future researchers to beat.     

Evolutionary crew scheduling with adaptive chromosomes

This paper presents an adaptive evolutionary approach incorporating a hybrid genetic algorithm (GA) for public transport crew scheduling problems, which are well-known to be NP-hard. To ensure the search efficiency, a suitable chromosome representation has to be determined first. Unlike a canonical GA for crew scheduling where the chromosome length is fixed, the chromosome length in the proposed approach may vary adaptively during the iterative process, and its initial value is elaborately designated as the lower bound of the number of shifts to be used in an unachievable optimal solution. Next, the hybrid GA with such a short chromosome length is employed to find a feasible schedule. During the GA process, the adaptation on chromosome lengths is achieved by genetic operations of crossover and mutation with removal and replenishment strategies aided by a simple greedy algorithm. If a feasible schedule cannot be found when the GA’s termination condition is met, the GA will restart with one more gene added. The above process is repeated until a feasible solution is found. Computational experiments based on 11 real-world crew scheduling problems in China show that, compared to a fuzzy GA known to be well performed for crew scheduling, better solutions are found for all the testing problems. Moreover, the algorithm works fast, has achieved results close to the lower bounds obtained by a standard linear programming solver in terms of the number of shifts, and has much potential for future developments.     

公交车辆智能调度研究

根据智能交通系统ITS(Intelligent Transport Systems)研究发展状况以及我国ITS研 究开发的主要内容和公交公司实际运输的基本需求采用遗传算法GA(Genetic Algorithm)进 行了公交车辆智能调度方法的研究.该方法充分利用遗传算法的智能化特征,有效地改善公交 车辆的静态调度,提高公交车辆的运营效率.为避免遗传算法的早熟问题,运用混合遗传算法 HGA(Hybrid Genetic Algorithm),提高遗传算法的收敛性能和优化质量,以确保遗传算法的优化性能.在静态调度方法的基础上,针对公交车辆运营调度管理特点,借助通信技术、计算机技术以及自动控制技术,分析研究了公文车辆的动态调度的实现方法,从而进一步提高公交车辆运营调度管理效率,为公交车辆智能化调度系统的实施做好必要的技术服务.     

C-V2X应用场景的算法建模及评价模型综述

V2X利用无线信息交互技术,实现车与其他实体之间的信息交互,将"人、车、路、云"交通参与要素有机地联系在一起,构建一个智慧的交通体系。算法的评价基于算法建模,通过建模梳理算法的逻辑思路,输出算法相关的标定参数,进而使算法性能达到更优。基于C-V2X应用场景的算法评价模型,旨在研究如何评判不同应用场景的实现优劣,用于设计出标准的指标参数衡量算法的性能,重点从算法计算效率和算法有效性2个维度考虑,构建起评估算法功能及性能的立体模型,多角度权衡并分析,从而对应用场景的实现给予评估反馈。     

Operational surface drift prediction using linear and non-linear hyper-ensemble statistics on atmospheric and ocean models

Multimodel super-ensemble forecasts, which exploit the power of an optimal local combination of individual models usually show superior forecasting skills when compared to individual models because they allow for local correction and/or bias removal. Deterministic approaches to the problem of surface drift are often limited by strong assumptions on the underlying physics. A new approach based on linear and non-linear optimization is proposed, using hyper-ensemble deduced statistics to forecast at short time scale Lagrangian drifts from combined atmospheric and ocean operational models and local observations that were made available during the MREA04 field experiment along the West coast of Portugal. Optimization methods are based on a training/forecast cycle. The performance and the limitations of the hyper-ensembles and the individual models are discussed. Results suggest that our statistical methods reduce the position errors significantly for 12 to 48 h forecasts and hence compete with pure deterministic approaches.     

基于能耗最优化的动力定位推力分配逻辑算法研究

文章为动力定位系统执行器的设计提供了两种推力分配最优化的求解方法,旨在寻求一种理想的推力器输出,包括推力与方位角,以维持动力定位系统能力。通过求解非线性约束最优化问题,得出时效性、稳定性与可控制性强的推力分配模块。文中采用一个或若干个合适的结构矩阵来描述推力器的位置及其性能,采用不同的边界条件对系统要求进行描述,如降低推力损失等。基于一个简单的算例,分别采用遗传算法和序列二次方法进行求解,改变约束条件并分析程序运行结果,对比信号输出及其能耗情况,论证两种算法的可行性与稳定性。文中还对比了五种不同的情况,包括约束条件以及算法的变化,以满足不同的应用需求。     

Intermodal hub-and-spoke network design: Incorporating multiple stakeholders and multi-type containers

This paper develops a mathematical program with equilibrium constraints (MPEC) model for the intermodal hub-and-spoke network design (IHSND) problem with multiple stakeholders and multi-type containers. The model incorporates a parametric variational inequality (VI) that formulates the user equilibrium (UE) behavior of intermodal operators in route choice for any given network design decision of the network planner. The model also uses a cost function that is capable of reflecting the transition from scale economies to scale diseconomies in distinct flow regimes for carriers or hub operators, and a disutility function integrating actual transportation charges and congestion impacts for intermodal operators. To solve the MPEC model, a hybrid genetic algorithm (HGA) embedded with a diagonalization method for solving the parametric VI is proposed. Finally, the comparative analysis of the HGA and an exhaustive enumeration algorithm indicates a good performance of the HGA in terms of computational time and solution quality. The HGA is also applied to solve a large-scale problem to show the applicability of the proposed model and algorithm.     

Modeling a rail transit alignment considering different objectives

An optimization model for station locations for an on-ground rail transit line is developed using different objective functions of demand and cost as both influence the planning of a rail transit alignment. A microscopic analysis is performed to develop a rail transit alignment in a given corridor considering a many-to-one travel demand pattern. A variable demand case is considered as it replicates a realistic scenario for planning a rail transit line. A Genetic Algorithm (GA) based on a Geographical Information System (GIS) database is developed to optimize the station locations for a rail transit alignment. The first objective is to minimize the total system cost per person, which is a function of user cost, operator cost, and location cost. The second objective is to maximize the ridership or the service coverage of the rail transit alignment. The user cost per person is minimized separately as the third objective because the user cost is one of the most important decision-making factors for planning a transit system from the users’ perspective. A transit planner can make an informed decision between various alternatives based on the results obtained using different objective functions. The model is applied in a case study in the Washington, DC area. The optimal locations and sequence of stations obtained using the three objective functions are presented and a comparative study between the results obtained is shown in the paper. In future works we will develop a combinatorial optimization problem using the aforementioned objectives for the rail transit alignment planning and design problem.     

高速公路入口匝道的协调优化控制

为了实施高速公路路网交通流的优化控制,采用MATANET模型进行路网交通流建模,应用非线性最优控制方法,构造了路网入口匝道的协调控制模型。该模型应用全局实时交通数据,以总费用时间与密度控制的组合构建性能指标,能够提高交通运行效率,并有效处理交通拥挤。针对模型的非线性,应用遗传算法对性能指标进行优化,探究TTS-密度控制指标的优化对路网交通拥挤状况的控制效果。以南京市周边高速公路路网作为应用实例,验证了所研究模型与优化方法的可行性。     

有运送路径限制的多品种流交通网络最小费用流算法研究

传统的交通网络最小费用流分配是针对单一品种,但在实际的交通运输应用中,交通网络中往往会出现多品种流的运送情况,而且也有可能对某些品种的运送路径进行限制.首先针对交通网络中的多品种流及其流动现象进行分析,借鉴Ford-Fulkerson算法中构造伴随增流网络的思路,建立了多品种流交通网络图的顺推重构方法,在此基础上,构造了有运送路径限制的多品种流交通网络最小费用流算法.在交通运输领域,多品种流最小费用流问题普遍存在,此算法为解决实际交通网络的相关问题提供了基础.