北京航空航天大学学报 ›› 2019, Vol. 45 ›› Issue (1): 26-34.doi: 10.13700/j.bh.1001-5965.2018.0259

• 论文 • 上一篇    下一篇

基于双层K近邻算法航站楼短时客流量预测

邢志伟1,2, 何川1,2, 罗谦2,3, 蒋祥枫2, 刘畅2, 丛婉2   

  1. 1. 中国民航大学 电子信息与自动化学院, 天津 300300;
    2. 中国民用航空局第二研究所, 成都 610041;
    3. 民航成都信息技术有限责任公司, 成都 611430
  • 收稿日期:2018-05-07 修回日期:2018-07-28 出版日期:2019-01-20 发布日期:2019-01-28
  • 通讯作者: 罗谦 E-mail:luoqian@caacetc.com
  • 作者简介:邢志伟,男,博士,教授。主要研究方向:民航智能规划与调度、民航装备与系统;何川,男,硕士研究生。主要研究方向:机场运行与控制工程;罗谦,男,博士,研究员。主要研究方向:机场运营管理、民航智能规划与调度;蒋祥枫,男,硕士,高级工程师。主要研究方向:民航智能规划与调度;刘畅,男,硕士,工程师。主要研究方向:机场运行与控制工程;丛婉,女,硕士。主要研究方向:通信工程、电子信息。
  • 基金资助:
    国家自然科学基金(U1533203);民航安全能力建设资金(FDSA0032);四川省科技支撑计划(2016GZ0068);成都市战略性新兴产品研发补贴项目(2015-CP01-00158-GX)

Terminal building short-term passenger flow forecast based on two-tier K-nearest neighbor algorithm

XING Zhiwei1,2, HE Chuan1,2, LUO Qian2,3, JIANG Xiangfeng2, LIU Chang2, CONG Wan2   

  1. 1. Electronic Information and Automation Institute, Civil Aviation University of China, Tianjin 300300, China;
    2. The Second Research Institute of Civil Aviation Administration of China, Chengdu 610041, China;
    3. Civil Aviation Information Technology Co., Ltd., Chengdu 611430, China
  • Received:2018-05-07 Revised:2018-07-28 Online:2019-01-20 Published:2019-01-28
  • Supported by:
    National Natural Science Foundation of China (U1533203); Safety Capacity Constructing Funds Project of CAAC (FDSA0032); Science and Technology Support Program of Sichuan Province (2016GZ0068); Strategic Emerging Product R & D Subsidy Project of Chengdu (2015-CP01-00158-GX)

摘要: 航站楼离港客流量在短时期内呈现准周期性规律变化,易受航班计划、天气等多种因素影响,表现出复杂的非线性特点。为了实现航站楼短时客流量的准确预测,在传统K近邻(KNN)算法基础上增加了航班计划状态模式匹配方法,以航班计划包含的多维属性作为特征选取相似历史运营日作为预测基准向量,建立基于航站楼短时客流量预测的双层K近邻模型。通过实例分析,与ARIMA模型和传统K近邻模型等进行比较,证明双层K近邻模型预测误差更小,精度更高,模型拟合度相对传统K近邻模型提高了8%~10%,为航站楼短时客流量精确预测提供了一种新的解决思路。

关键词: 航站楼客流量, 短时预测, 模式匹配, 预测模型, 双层K近邻

Abstract: Outbound passenger flow of terminal building shows the quasi-periodic variation in a short period of time and also shows complex nonlinear characteristics because of many factors such as flight schedule and weather. In order to accurately predict the short-term passenger flow of terminal building, the flight schedule state pattern matching procedure is added on the basis of the traditional K-nearest neighbor (KNN) algorithm. The flight schedule including multi-dimensional attributes is taken as a feature to select historical similar operation days as forecast reference vectors. The two-tier K-nearest neighbor model based on terminal building short-term passenger flow forecast is built. Through instance analysis and comparison with ARIMA model and traditional K-nearest neighbor model, it is proved that two-tier K-nearest neighbor model has smaller prediction error and higher precision, and the model fitting degree increases by 8%-10% compared with traditional K-nearest neighbor model. Thus the model provides a new solution for accurately forecasting terminal building short-term passenger flow.

Key words: passenger flow of terminal building, short-term forecast, pattern matching, forecast model, two-tier K-nearest neighbor

中图分类号: 


版权所有 © 《北京航空航天大学学报》编辑部
通讯地址:北京市海淀区学院路37号 北京航空航天大学学报编辑部 邮编:100191 E-mail:jbuaa@buaa.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发