基于二次分解策略和模糊时间序列模型的航空客运需求预测研究

doi:10.16381/j.cnki.issn1003-207x.2019.1100

中国管理科学 ›› 2020, Vol. 28 ›› Issue (12): 108-117.doi: 10.16381/j.cnki.issn1003-207x.2019.1100

基于二次分解策略和模糊时间序列模型的航空客运需求预测研究

梁小珍¹, 邬志坤¹, 杨明歌¹, 汪寿阳^2,3

1. 上海大学管理学院, 上海 200444;
2. 中国科学院大学经济与管理学院, 北京 100190;
3. 中国科学院数学与系统科学研究院, 北京 100190

收稿日期:2019-07-26 修回日期:2019-10-30 出版日期:2020-12-20 发布日期:2021-01-11
通讯作者: 汪寿阳(1958-),男(汉族),江苏东台人,中国科学院大学经济与管理学院,研究员,研究方向:经济预测、金融风险管理,E-mail:sywang@amss.ac.cn. E-mail:sywang@amss.ac.cn
基金资助:
国家自然科学基金资助项目（71701122，71702095，11801352）

Air Passenger Demand Forecasting Based on a Dual Decomposition Strategy and Fuzzy Time Series Model

LIANG Xiao-zhen¹, WU Zhi-kun¹, YANG Ming-ge¹, WANG Shou-yang^2,3

1. School of Management, Shanghai University, Shanghai 200444, China;
2. School of Economics and Management, University of Chinese Academy of Sciences, Beijing 100190, China;
3. Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing 100190, China

Received:2019-07-26 Revised:2019-10-30 Online:2020-12-20 Published:2021-01-11

摘要/Abstract

摘要： 提高航空客运需求预测的准确性对于航空公司以及整个航空运输系统的发展都具有重要的现实意义。以往研究普遍采用单一分解策略去处理航空客运需求时序中存在的复杂特征，以此提升组合模型的预测性能。然而传统的分解策略存在着特征提取不完全、分解方法带有固有缺陷等问题，导致组合模型预测效果不能得到充分的提升。为此，本文提出一种基于二次分解策略和模糊时间序列模型的航空客运需求预测方法。该方法首先利用季节调整模型（X12-ARIMA）将原始时序分解成季节成分序列与季节调整后序列，继而利用改进的自适应噪声集成经验模态分解方法（ICEEMDAN）将季节调整后序列分解成一系列不同时间尺度的本征模态函数（IMF）和残差序列（Residue）。然后使用基于模糊C均值算法（FCM）划分论域区间的FTS模型对季节成分序列、各IMF分量以及残差序列分别进行预测。最后将各分量序列的预测结果进行集成，重构出航空客运需求的预测值。实证结果表明，本文所提出的二次分解策略表现显著优于传统的分解策略，并且本文所提出模型对于航空客运需求预测有着较高的准确性。

关键词: 航空客运需求预测, 季节调整, 自适应噪声集成经验模态分解, 模糊C均值算法, 模糊时间序列模型

Abstract: Improving the accuracy of air passenger demand forecasting plays a crucial role in the development of airlines and the whole air transport system,which is of great political and economic significance for all of society but is still a challenging task.In previous studies, individual decomposition strategy has been adopted generally to deal with the complex features inair passenger demand series, so as to improve the prediction performance of the hybrid model. However, the traditional decomposition strategy has some drawbacks such as incomplete feature extraction and the inherent defects in the decomposition method, which lead to the inadequate improvement of the prediction effect of the hybrid model.Therefore, a method for air passenger demand forecasting based on a dual decomposition strategy and a fuzzy time series modelis proposed.Firstly, a seasonal adjustment model (X12-ARIMA) is applied to decompose the original series into a seasonal component and a seasonally adjusted series. Then the improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) is used to decompose the seasonally adjusted series into several intrinsic mode functions (IMFs) with different time scales and a residue.After that, the FTS model with fuzzy c-means algorithm (FCM) partitioning intervals is used to forecast each IMF component, the residue and the seasonal component. Finally, the prediction of air passenger traffic is obtained by integrating the above results.Case studies utilizing monthly air passenger demand data collected from Shanghai Pudong International Airport, Chengdu Shuangliu International Airport and Shenzhen Bao'an International Airport are employed as examples. The empirical results show that the dual decomposition strategy proposed in this paper is significantly better than the traditional decomposition strategy, and the proposed model outperforms all of the considered comparison models. The proposed model can be used to improve the accuracy of air passenger demand prediction.

Key words: forecast of air passenger demand, seasonal adjustment, improved complete ensemble empirical mode decomposition with adaptive noise, fuzzy c-means algorithm, fuzzy time series model

中图分类号:

F562.8

梁小珍, 邬志坤, 杨明歌, 汪寿阳. 基于二次分解策略和模糊时间序列模型的航空客运需求预测研究[J]. 中国管理科学, 2020, 28(12): 108-117.

LIANG Xiao-zhen, WU Zhi-kun, YANG Ming-ge, WANG Shou-yang. Air Passenger Demand Forecasting Based on a Dual Decomposition Strategy and Fuzzy Time Series Model[J]. Chinese Journal of Management Science, 2020, 28(12): 108-117.

参考文献

[1] Kim S D, Shin D H.Forecasting short-term air passenger demand using big data from search engine queries[J]. Automation in Construction, 2016, 70:98-108.
[2] Hofer C, Kali R, Mendez F. Socio-economic mobility and air passenger demand in the U.S.[J]. Transportation Research Part A, 2018, 112:85-94.
[3] Profillidis VΑ. An ex-post assessment of a passenger demand forecast of an airport[J]. Journal of Air Transport Management, 2012, 25:47-49.
[4] Huang Anqiang, Qiao Han, Wang Shouyang, et al. Improving forecasting performance by exploiting expert knowledge:Evidence from Guangzhou port[J]. International Journal of Information Technology & Decision Making, 2016, 15(2):387-401.
[5] Huang Anqiang, Lai K K, Qiao Han, et al. Does interval knowledge sharpen forecasting models? Evidence from China's typical ports[J]. International Journal of Information Technology & Decision Making, 2018, 17(2):467-483.
[6] Tsui W H K, Ozer B H, Gilbey A, et al. Forecasting of Hong Kong airport's passenger throughput[J]. Tourism Management, 2014, 42:62-76.
[7] Dantas T M, Cyrino O F L, Varela R H M. Air transportation demand forecast through Bagging Holt Winters methods[J]. Journal of Air Transport Management, 2017, 59:116-123.
[8] Guo Rui, Zhong Zhiwen. Forecasting air passenger volume in Singapore:Determining the explanatory variables for econometric models[J]. MATTER:International Journal of Science and Technology, 2017, 3(1):123-139.
[9] Qin Lan, Li Weide, Li Shijia. Effective passenger flow forecasting using STL and ESN based on two improvement strategies[J]. Neurocomputing, 2019, 356:244-256.
[10] 汤铃,李建平,孙晓蕾,等.基于模态分解的国家风险多尺度特征分析[J].管理评论,2012,24(8):3-10.
[11] 孙晓蕾,姚晓阳,杨玉英,等.国家风险动态性的多尺度特征提取与识别:以OPEC国家为例[J].中国管理科学,2015,23(4):1-10.
[12] Wang Jianzhou, Yang Wendong, Du Pei, et al. Research and application of a hybrid forecasting framework based on multi-objective optimization for electrical power system[J]. Energy, 2018, 148:59-78.
[13] 梁小珍, 乔晗, 汪寿阳, 等. 基于奇异谱分析的我国航空客运量集成预测模型[J]. 系统工程理论与实践, 2017, 37(6):1479-1488.
[14] 肖进,孙海燕,刘敦虎,等.基于GMDH混合模型的能源消费量预测研究[J].中国管理科学,2017,25(12):158-166.
[15] Bao Yukun, Xiong Tao, Hu Zhongyi. Forecasting air passenger traffic by support vector machines with ensemble empirical mode decomposition and slope-based method[J]. Discrete Dynamics in Nature and Society,vol. 2012, Article ID 431512, 12 pages, 2012. https://doi.org/10.1155/2012/431512.
[16] Xie Gang, Wang Shouyang, Lai K K. Short-term forecasting of air passenger by using hybrid seasonal decomposition and least squares support vector regression approaches[J]. Journal of Air Transport Management, 2014, 37:20-26.
[17] 潘和平,张承钊.FEPA-金融时间序列自适应组合预测模型[J].中国管理科学,2018,26(6):26-38.
[18] 苏振宇,龙勇,汪於. 基于季节调整和Holt-Winters的月度负荷预测方法[J]. 中国管理科学, 2019, 27(3):30-40.
[19] Wu Zhaohua, Huang N E. Ensembleempiricalmodedecomposition:anoise-assisteddataanalysismethod[J]. Advances in Adaptive Data Analysis, 2009, 1(1):1-41.
[20] Torres M E,Colominas M A, Schlotthauer G, et al. A completeensembleempirical mode decompositionwithadaptivenoise[C]//Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing,Prague, Czech Republic, May 22-27, 2011.
[21] Colominas M A, Schlotthauer G, Torres M E. Improved complete ensemble EMD:A suitable tool for biomedical signal processing[J]. Biomedical Signal Processing and Control, 2014, 14:19-29.
[22] Xu Yunzhen, Yang Wendong, Wang Jianzhou. Air quality early-warning system for cities in China[J]. Atmospheric Environment, 2017, 148:239-257.
[23] 贾逸伦, 龚庆武, 李俊雄, 等. 基于CEEMDAN与量子粒子支持向量机的电力负荷组合预测[J]. 电测与仪表, 2017, 54(1):16-21.
[24] Zadeh L A. Fuzzysets[J]. Information & Control, 1965, 8(3):338-353.
[25] Song Qiang, Chissom B S. Forecasting enrollments with fuzzy time series-Part I[J]. Fuzzy Sets and Systems, 1993, 54(1):1-9.
[26] Song Qiang, Chissom B S. Forecasting enrollments with fuzzy time series-Part II[J]. Fuzzy Sets and Systems, 1994, 62(1):1-8.
[27] 刘智,张铁,董莹,等.关于股票价格的二阶模糊时间序列[J].东北大学学报(自然科学版),2019,40(2):300-304.
[28] 丁欣,谢祥俊,赵春兰,等.基于动态隶属度的模糊时间序列在我国居民消费水平预测上的应用[J].模糊系统与数学,2019,33(1):164-174.
[29] Bezdek J C. Pattern recognition with fuzzy objective function algorithms[J]. Advanced Applications in Pattern Recognition, 1981, 22(1171):203-239.
[30] 邱望仁, 刘晓东. 模糊时间序列模型研究综述[J]. 模糊系统与数学, 2014, 28(3):173-181.
[31] Chen Shyiming. Forecasting enrollments based on fuzzy time series[J]. Fuzzy Sets & Systems, 1996, 81(3):311-319.
[32] Song Qiang. Seasonal forecasting in fuzzy time series[J]. Fuzzy Sets and Systems, 1999, 107(2):235-236.
[33] Diebold F X, Mariano R S. Comparing predictive accuracy. Journal of Business & Economic Statistics, 1995, 13(3):253-263.

基于二次分解策略和模糊时间序列模型的航空客运需求预测研究

Air Passenger Demand Forecasting Based on a Dual Decomposition Strategy and Fuzzy Time Series Model

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

Metrics

本文评价

推荐阅读 10