基于自动编码器的时间序列预测混合模型  

Hybrid Model for Time Series Prediction Based on Autoencoder

作　　者：路强[1] 滕进风 黎杰[1] 凌亮 丁超 黄健刚 LU Qiang;TENG Jin-Feng;LI Jie;LING Liang;DING Chao;HUANG Jian-Gang(School of Computer Science and Information Engineering,Hefei University of Technology,Hefei 230009,China;Huangshan Tourism Group Hydropower Development Co.Ltd.,Huangshan 245899,China;School of Economics and Management,Nanjing University of Aeronautics and Astronautics,Nanjing 211106,China)

机构地区：[1]合肥工业大学计算机与信息学院,合肥230009 [2]黄山旅游集团水电开发有限公司,黄山245899 [3]南京航空航天大学经济与管理学院,南京211106

出　　处：《计算机系统应用》2022年第7期55-65,共11页Computer Systems & Applications

基　　金：安徽省重点研发计划(201904D07010);黄山市科技计划(2019KN-05);合肥工业大学智能制造研究院科技成果培养(IMIPY2021022)。

摘　　要：时间序列预测目前在众多领域有着广泛应用.如果可以准确估计事件或指标的未来发展,它可以帮助人们做出重要的决定.然而对不同时间序列建立模型并准确预测已成为最具挑战的应用之一.因此,本文提出了一种新颖的混合多步预测模型,称为SSA-ConvBiAE.首先,通过奇异谱分析(SSA)将原始数据分解为不同的趋势分量.其次,设计了新的基于卷积长短期记忆(ConvLSTM)和双向门控循环单元(BiGRU)的自动编码器网络结构.最后,将不同的分量分别输入到对应的自动编码器中进行训练和预测并求和预测结果.为了评价模型的预测性能,在真实的供水数据集和公开的时间序列数据集上进行了实验,实验结果表明,模型的预测结果优于基线方法.本文已在网站https://github.com/VIMLab-hfut/SSA-ConvBiAE上发布了源代码.Time series prediction currently has a wide range of applications in many fields.It can help people make important decisions if they can accurately estimate the future development of events or indicators.However,modeling and accurately predicting time series with different features has become one of the most challenging applications.Therefore,a novel hybrid multi-step prediction model is proposed,called SSA-ConvBiAE.Firstly,the original data is decomposed into different trend components by singular spectrum analysis(SSA).Secondly,we design a new autoencoder network structure based on convolutional long short-term memory(ConvLSTM)and bidirectional gated recurrent unit(BiGRU).Finally,the different components are inputted to the corresponding autoencoders for training and prediction,and the prediction results are fused.To evaluate the predictive performance of our model,we conduct experiments on two real water supply datasets and two publicly available time series datasets.Experimental results show that the proposed model achieves better performance than baseline methods.The source code has been published on https://github.com/VIMLabhfut/SSA-ConvBiAE.

关 键 词：时间序列预测 混合模型 奇异谱分析 数据分解 自动编码器 

分 类 号：O211.6[理学—概率论与数理统计]