基于聚类分析的公交线路资源配置时段划分方法——以烟台市为例

Time Division Method of Bus Route Resource Allocation Based on Cluster Analysis:A Case Study of Yantai

为节约公交运营成本、提升其服务质量和效率,需合理配置公交线路资源。鉴于此,基于烟台市公交刷卡数据和移动支付数据,通过数据匹配、合并及扩样等方法进行数据处理,获取完整的公交线路客流信息,分析一天内及周内各天公交客运量的变化特征。在此基础上,以半小时线路客运量为基础,基于有序聚类法进行公交线路资源配置时段划分,并提出对应时段的公交运营调度方法;最后利用贝塔系数法确定配置时段最优分段数。研究发现,烟台市工作日、周末和节假日常规公交线路资源配置可分别划分为5个、4个和3个时间段,聚类结果F检验显著性水平大于0.05且满足客流变化特征,说明有序聚类法能对公交线路资源配置时段进行有效划分。

In order to save the operation cost of urban bus and improve its service quality and efficiency,it is necessary to reasonably allocate bus line resources.Given this,the paper based on the card reading data and mobile payment data of Yantai bus,processed the data by matching,merging and sample enlargement,obtained the complete information of bus line passenger flow,and analyzed the characteristics of the variation of bus passenger flow in one day and each day of a week.Based on the passenger volume of half an hour,the paper analyzed the time division of bus line resource allocation by the ordered clustering method,and proposed the bus operation scheduling method of corresponding period.The method ofβvalue was used to determine the optimal segments of the configuration period.The results showed that the resource allocation periods of bus lines in Yantai on weekdays,weekends and holidays could be divided into 5,4 and 3 periods respectively;the F-test significance level of clustering results was greater than 0.05,and could meet the characteristics of passenger flow variation.It is proved that the ordered clustering method can effectively divide the time period of bus line resource allocation.