计算机工程与应用 ›› 2020, Vol. 56 ›› Issue (15): 235-241.DOI: 10.3778/j.issn.1002-8331.1905-0184

• 工程与应用 • 上一篇    下一篇

传感网中数据驱动的多时段控制方法优化研究

徐琛,董德存,欧冬秀   

  1. 同济大学 道路与交通工程教育部重点实验室,上海市轨道交通结构耐久与系统安全重点实验室,上海 201804
  • 出版日期:2020-08-01 发布日期:2020-07-30

Time-of-Day Control Optimization of Data-Driven Urban Road Constant-Peak-Type Intersections in Sensor Networks

XU Chen, DONG Decun, OU Dongxiu   

  1. The Key Laboratory of Road and Traffic Engineering, Ministry of Education, School of Transportation Engineering, Shanghai Key Laboratory of Rail Infrastructure Durability and System Safety, Tongji University, Shanghai 201804, China
  • Online:2020-08-01 Published:2020-07-30

摘要:

为了克服“常峰型”交叉口多时段控制时段划分单因素划分方法的趋同性与多因素划分方法的过复杂性,提出了一种基于传感网数据采集技术与数据驱动理论的“常峰型”交叉口多时段控制时段划分优化方法。以传感网感知能力对传统交通流量数据增加维度,引入交叉口交通流三维向量,以向量的形式表示在某一交叉口某一段时间内的交通总流量的大小、方向及与冲突点的平均时间距离。运用时间序列自回归滑动平均算法对相邻向量间距离进行归并得出时段划分优化方案。以某城市实际交通流量数据为测试数据进行评价对比分析。结果表明,创新模型运用在“常峰型”交叉口,与传统方法相比其控制效果更加准确高效,交叉口全天总延误时间有效降低约6.04%。

关键词: 交通信号控制, 多时段控制, 数据驱动, 传感网

Abstract:

In order to overcome the complexity of the single factor and multi-factor method of time-of-day control in the constant-peak-type intersections, this paper proposes a novel optimization model of the division of time-of-day control segmented points of constant-peak-type intersections based on sensor networks and data-driven. The dimension of traditional traffic flow data is increased by sensor networks, and a vector quantity is developed to represent the size, direction, and average time frequency with conflict point traffic of the total traffic flow at a certain intersection for a period by introducing a 3D vector of intersection traffic flow. A time-series segmentation algorithm is used to merge the distances between adjacent 3D vectors to obtain the time-of-day control scheme. The actual traffic flow data of a city in 2016 is used as the test data for comparative analysis. It is shown that when the innovated double-order optimization model is used  in the intersection according to the constant-peak-type traffic flow characteristic, its control is more accurate and efficient than that of the traditional total flow segmentation model. The total delay time is reduced by approximately 6.04%.

Key words: traffic signal control, time-of-day control, data-driven, sensor networks