考虑交通大数据的交通检测器优化布置模型  

Optimal traffic sensor layout model considering traffic big data

作　　者：孙智源[1] 陆化普[1] 

机构地区：[1]清华大学土木工程系,交通研究所,北京100084

出　　处：《清华大学学报（自然科学版）》2016年第7期743-750,共8页Journal of Tsinghua University(Science and Technology)

基　　金：“十二五”国家科技支撑计划资助项目(2014BAG01B04);清华大学苏州汽车研究院(吴江)返校经费课题(2015WJB-02)

摘　　要：为了提高城市交通信息采集的准确性、可靠性和经济性,提出了一种交通检测器优化布置模型。大数据背景下,考虑系统成本、多源数据共享、数据需求、检测器故障、道路基础设施、检测器类型等因素,构建了交通检测器布置的影响因素集。综合分析各个影响因素,提出了由最小系统成本优化、最大截断流优化、最小包含路径优化和OD(origin-destination)覆盖约束构成的多目标优化模型。应用基于遗传算法的宽容分层序列法,对模型进行求解。算例研究表明:该文的模型实现了多目标的优化,反映了多源数据共享和检测器故障的影响,满足了OD覆盖约束,可达到交通检测器的优化布置。An optimal traffic sensor layout model was developed to improve the accuracy, reliability and economy of urban traffic information collection. The traffic sensor layout was optimized in light of big data traffic information with the system optimized with consideration of the system cost, multi-source data sharing, data demand, fault conditions, road infrastructure, and different types of sensors. The impact of these influential factors was taken into account in a multi-objective programming model that included system cost minimization, traffic flow intercept maximization, path coverage minimization, and an origin-destination（OD） coverage constraint. The model was solved by the tolerant lexicographic method based on a genetic algorithm. A case study shows that the model provides multi-objective optimization, reflects the influence of multi-source data sharing and fault conditions, satisfies the origin-destination coverage constraint, and provides the optimal traffic sensor layout.

关 键 词：交通调查 交通检测器优化布置 多目标优化 交通大数据 遗传算法 宽容分层序列 

分 类 号：U491.11[交通运输工程—交通运输规划与管理]