基于k-means聚类的停车分区方法研究及应用——以广州市为例  

Study and Application of Zoning for Parking Method Based on K-means Clustering:A Case Study of Guangzhou

作　　者：张海霞 段亦峰 杜刚诚 

机构地区：[1]广州市交通规划研究院有限公司

出　　处：《交通与港航》2024年第6期99-105,共7页Communication & Shipping

摘　　要：提出基于k-means聚类的面向实施管理的三步骤方法,第一步构造“理论型”停车分区,第二步建立管理边界网络,第三步重构“治理型”停车分区。以广州市为例,构造了分层差异显著的三分类停车供给管理分区,验证了方法的有效性,提出差异化的配建指标,成果纳入广州市建设项目停车配建指标规定并得到印发实施。该方法还可用于收费、治理、需求管理等场景和其他城市交通领域,具有广泛和迫切的应用前景。A three-step zoning for parking method based on k-means clustering and oriented towards implementation management is proposed.Firstly,theory-based parking zones are constructed.Secondly,management boundaries network is built.Finally,governance-based parking zones are reconstructed.Taking Guangzhou as an example,a three-tiered parking supply management zones with significant hierarchical differences are constructed,validating the effectiveness of this method.And different parking allocation standards are proposed.The research achievements have been incorporated into the parking allocation standards stipulated for construction projects in Guangzhou and promulgated for implementation.This method can be applied to various scenarios,including parking fee,parking management,parking demand control,and other urban domains,demonstrating its broad and urgent application prospects.

关 键 词：停车分区 聚类算法 分区映射 停车管理 广州 

分 类 号：U491.7[交通运输工程—交通运输规划与管理]