《计算机应用》唯一官方网站 ›› 2022, Vol. 42 ›› Issue (12): 3931-3940.DOI: 10.11772/j.issn.1001-9081.2021101716

• 前沿与综合应用 • 上一篇    

基于二次分解重构策略的航空客流需求预测

栗慧琳(), 李洪涛, 李智   

  1. 兰州交通大学 交通运输学院,兰州 730070
  • 收稿日期:2021-10-08 修回日期:2022-01-04 接受日期:2022-01-24 发布日期:2022-04-08 出版日期:2022-12-10
  • 通讯作者: 栗慧琳
  • 作者简介:李洪涛(1976—),男,河南漯河人,教授,博士,主要研究方向:机器学习、预测理论与方法、预测与决策
    李智(1996—),女,河南南阳人,硕士研究生,主要研究方向:时间序列分析及应用、人工智能。
  • 基金资助:
    国家自然科学基金资助项目(72161022);甘肃省自然科学基金资助项目(20JR5RA394)

Air passenger demand forecasting based on dual decomposition and reconstruction strategy

Huilin LI(), Hongtao LI, Zhi LI   

  1. School of Traffic and Transportation,Lanzhou Jiaotong University,Lanzhou Gansu 730070,China
  • Received:2021-10-08 Revised:2022-01-04 Accepted:2022-01-24 Online:2022-04-08 Published:2022-12-10
  • Contact: Huilin LI
  • About author:LI Hongtao born in 1976, Ph. D., professor. His research interests include machine learning, prediction theory and method,prediction and decision.
    LI Zhi,born in 1996, M. S. candidate. Her research interests include time series analysis and application, artificial intelligence.
  • Supported by:
    National Natural Science Foundation of China(72161022);Natural Science Foundation of Gansu Province(20JR5RA394)

摘要:

考虑到航空客流需求序列的季节性、非线性和非平稳等特点,提出了一个基于二次分解重构策略的航空客流需求预测模型。首先,通过STL和自适应噪声互补集成经验模态分解(CEEMDAN)方法对航空客流需求序列进行二次分解,并根据数据复杂度和相关度的特征分析结果进行分量重构;然后,采用模型匹配策略分别选取自回归单整移动平均季节(SARIMA)、自回归单整移动平均(ARIMA)、核极限学习机(KELM)和双向长短期记忆(BiLSTM)网络模型对各重构分量进行预测,其中KELM和BiLSTM模型的超参数通过自适应树Parzen估计(ATPE)算法确定;最后,将重构分量预测结果进行线性集成。以北京首都国际机场、深圳宝安国际机场和海口美兰国际机场的航空客流数据作为研究对象进行了1步和多步预测实验,实验结果表明,与一次分解集成模型STL-SAAB相比,所提模型的均方根误差(RMSE)提升了14.98%~60.72%。可见以“分而治之”思想为指导,所提模型结合模型匹配和重构策略挖掘出了数据的内在发展规律,从而为科学预判航空客流需求变化趋势提供了新思路。

关键词: 航空客流需求预测, 二次分解重构, 模型匹配, 深度学习, 多步预测

Abstract:

Considering the seasonal, nonlinear and non-stationary characteristics of air passenger demand series, an air passenger demand forecasting model based on a dual decomposition and reconstruction strategy was proposed. Firstly, the air passenger demand series was decomposed twice by Seasonal and Trend decomposition using Loess (STL) and Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) methods, and the components were reconstructed based on the feature analysis results of complexity and correlation. Then, Seasonal AutoRegressive Integrated Moving Average (SARIMA), AutoRegressive Integrated Moving Average (ARIMA), Kernel based Extreme Learning Machine (KELM) and Bidirectional Long Short-Term Memory (BiLSTM) network models were selected by model matching strategy to predict each reconstructed component respectively, among which the hyperparameters of KELM and BiLSTM models were determined by the Adaptive Tree of Parzen Estimators (ATPE) algorithm. Finally, the prediction results of the reconstruction components were linearly integrated. The air passenger demand data collected from Beijing Capital International Airport, Shenzhen Bao’an International Airport and Haikou Meilan International Airport were taken as research subjects for one-step and multi-step ahead prediction experiments. Experimental results show that compared with the single decomposition ensemble model STL-SAAB, the proposed model has the Root Mean Square Error (RMSE) improved by 14.98% to 60.72%. It can be seen that guided by the idea of “divide and rule”, the proposed model combines model matching and reconstruction strategies to extract the inherent development pattern of the data, which provides a new thinking to scientifically predict the change of air passenger demand.

Key words: air passenger demand forecasting, dual decomposition and reconstruction, model matching, deep learning, multi-step ahead prediction

中图分类号: