| 摘 要: 为了降低大城市市民出行成本，缓解公交企业运力压力，提出一种智能交通出行OD(Origin Destination,出行地和目的地)的公交调度优化算法，以公交出行OD客流预测和计划排班发车时间间隔为出发点，运用公交出行OD客流推导理论，构建智能交通出行OD的公交调度优化模型。通过获取个人OD数据，利用单条线路公交OD方法，实现全市公交OD矩阵推算。根据全市公交出行OD推算结果，求解公交调度模型，解决智能交通调度多目标规划和公交线网优化问题。通过仿真模拟试验，分析智能公交排班计划评价指标，计算车辆营运效率占比：自动排班仿真数据为79%，实际运营数据为73%；统计车辆高峰时段与全天营运车次占比：自动排班仿真数据为36.75%，实际运营数据为37.37%，满足智能公交计划排班评价指标的要求，实例证明模型和算法具有实用性和可靠性。 |
| 关键词: 智能交通；出行OD；公交调度；客流预测；调度计划 |
|
中图分类号: TP181
文献标识码: A
|
| 基金项目: 广东省应用型科技研发重大专项资金项目(2015B010131004). |
|
| Optimization Model and Evaluation Method of Smart Transportation Dynamic Scheduling |
|
CHEN Shenjin
|
(School of Electrical and Computer Engineering, Nanfang College Guangzhou, Guangzhou 510970, China )
chenshenjinlg@126.com
|
| Abstract: In order to reduce the travel cost of citizens in big cities and relieve the pressure on the capacity of public transportation enterprises, this paper proposes a bus scheduling optimization algorithm of smart transportation OD (Origin Destination). Based on the prediction of bus OD passenger flow and the scheduled departure time interval, the derivation theory of bus OD passenger flow is used to construct the bus scheduling optimization model of smart transportation OD. By obtaining personal OD data, using single line bus OD method, city bus OD matrix is calculated. According to the city's public bus travel OD calculation results, the bus scheduling model is solved, and the problems of multi-objective planning and bus network optimization in smart transportation scheduling are solved. Through the simulation test, the evaluation index of smart bus scheduling plan is analysed and the proportion of vehicle operation efficiency is calculated. The simulation data of automatic bus scheduling is 79% and the actual operation data is 73%. Statistics of the vehicle proportion in peak hours and all day operation times are as follows: the simulation data of automatic bus scheduling is 36.75% and the actual operation data is 37.37%. The proposed model meets the requirements of evaluation index for the smart public transportation plan. The real cases prove that the model and algorithm are practical and reliable. |
| Keywords: smart transportation; travel OD; bus scheduling; passenger flow forecast; scheduling pl |
