A Hybrid Method With Adaptive Sub-Series Clustering and Attention-Based Stacked Residual LSTMs for Multivariate Time Series Forecasting
Multivariate Time Series Forecasting (MTSF) has recently emerged its growing importance in many industries. However, how to reduce the influence of the noise components existing in time series on prediction and extract features effectively are still two challenges in MTSF. This paper focuses on thos...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9039658/ |
| _version_ | 1818933127446265856 |
|---|---|
| author | Fagui Liu Yunsheng Lu Muqing Cai |
| author_facet | Fagui Liu Yunsheng Lu Muqing Cai |
| author_sort | Fagui Liu |
| collection | DOAJ |
| description | Multivariate Time Series Forecasting (MTSF) has recently emerged its growing importance in many industries. However, how to reduce the influence of the noise components existing in time series on prediction and extract features effectively are still two challenges in MTSF. This paper focuses on those two challenges and proposes a new prediction method based on decomposition-ensemble framework called adaptive sub-series clustering-stacked residual LSTMs-multi-level attention mechanism (ASC-SRLSTMs-MLAttn). The method consists of three stages: decomposition, prediction, and ensemble. In the decomposition stage, the target series is decomposed by Ensemble Empirical Mode Decomposition into multiple sub-series, which will be clustered and reconstructed by the ASC algorithm to reduce the complexity and the time consumption of prediction. In the prediction stage, the sub-series and correlation series will be fed into SRLSTMs-MLAttn for sub-series prediction. The model is based on the encoder-decoder architecture with stacked residual LSTMs as the encoder, which can effectively capture the dependencies among multi variables and the temporal features from multivariate time series. Besides, a multi-level attention mechanism (MLAttn), which makes full use of the encoding information of the encoder, has been introduced to further improve the prediction performance of the model. In the ensemble stage, the predicted values of each sub-series will be summed to obtain the final prediction of the target time series. We also demonstrate the superiority and effectiveness of our proposed method on four public datasets via the conducted comparison experiment and ablation study. |
| first_indexed | 2024-12-20T04:43:26Z |
| format | Article |
| id | doaj.art-23ee92b4bc9347678475047c0da7a775 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-20T04:43:26Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-23ee92b4bc9347678475047c0da7a7752022-12-21T19:53:04ZengIEEEIEEE Access2169-35362020-01-018624236243810.1109/ACCESS.2020.29815069039658A Hybrid Method With Adaptive Sub-Series Clustering and Attention-Based Stacked Residual LSTMs for Multivariate Time Series ForecastingFagui Liu0https://orcid.org/0000-0003-1135-4982Yunsheng Lu1https://orcid.org/0000-0001-9237-6707Muqing Cai2https://orcid.org/0000-0002-8863-2576School of Computer Science and Engineering, South China University of Technology, Guangzhou, ChinaSchool of Computer Science and Engineering, South China University of Technology, Guangzhou, ChinaSchool of Computer Science and Engineering, South China University of Technology, Guangzhou, ChinaMultivariate Time Series Forecasting (MTSF) has recently emerged its growing importance in many industries. However, how to reduce the influence of the noise components existing in time series on prediction and extract features effectively are still two challenges in MTSF. This paper focuses on those two challenges and proposes a new prediction method based on decomposition-ensemble framework called adaptive sub-series clustering-stacked residual LSTMs-multi-level attention mechanism (ASC-SRLSTMs-MLAttn). The method consists of three stages: decomposition, prediction, and ensemble. In the decomposition stage, the target series is decomposed by Ensemble Empirical Mode Decomposition into multiple sub-series, which will be clustered and reconstructed by the ASC algorithm to reduce the complexity and the time consumption of prediction. In the prediction stage, the sub-series and correlation series will be fed into SRLSTMs-MLAttn for sub-series prediction. The model is based on the encoder-decoder architecture with stacked residual LSTMs as the encoder, which can effectively capture the dependencies among multi variables and the temporal features from multivariate time series. Besides, a multi-level attention mechanism (MLAttn), which makes full use of the encoding information of the encoder, has been introduced to further improve the prediction performance of the model. In the ensemble stage, the predicted values of each sub-series will be summed to obtain the final prediction of the target time series. We also demonstrate the superiority and effectiveness of our proposed method on four public datasets via the conducted comparison experiment and ablation study.https://ieeexplore.ieee.org/document/9039658/Multivariate time series forecastingdecomposition-ensemble frameworkadaptive sub-series clustering algorithmstacked residual long short-term memorymulti-level attention mechanism |
| spellingShingle | Fagui Liu Yunsheng Lu Muqing Cai A Hybrid Method With Adaptive Sub-Series Clustering and Attention-Based Stacked Residual LSTMs for Multivariate Time Series Forecasting IEEE Access Multivariate time series forecasting decomposition-ensemble framework adaptive sub-series clustering algorithm stacked residual long short-term memory multi-level attention mechanism |
| title | A Hybrid Method With Adaptive Sub-Series Clustering and Attention-Based Stacked Residual LSTMs for Multivariate Time Series Forecasting |
| title_full | A Hybrid Method With Adaptive Sub-Series Clustering and Attention-Based Stacked Residual LSTMs for Multivariate Time Series Forecasting |
| title_fullStr | A Hybrid Method With Adaptive Sub-Series Clustering and Attention-Based Stacked Residual LSTMs for Multivariate Time Series Forecasting |
| title_full_unstemmed | A Hybrid Method With Adaptive Sub-Series Clustering and Attention-Based Stacked Residual LSTMs for Multivariate Time Series Forecasting |
| title_short | A Hybrid Method With Adaptive Sub-Series Clustering and Attention-Based Stacked Residual LSTMs for Multivariate Time Series Forecasting |
| title_sort | hybrid method with adaptive sub series clustering and attention based stacked residual lstms for multivariate time series forecasting |
| topic | Multivariate time series forecasting decomposition-ensemble framework adaptive sub-series clustering algorithm stacked residual long short-term memory multi-level attention mechanism |
| url | https://ieeexplore.ieee.org/document/9039658/ |
| work_keys_str_mv | AT faguiliu ahybridmethodwithadaptivesubseriesclusteringandattentionbasedstackedresiduallstmsformultivariatetimeseriesforecasting AT yunshenglu ahybridmethodwithadaptivesubseriesclusteringandattentionbasedstackedresiduallstmsformultivariatetimeseriesforecasting AT muqingcai ahybridmethodwithadaptivesubseriesclusteringandattentionbasedstackedresiduallstmsformultivariatetimeseriesforecasting AT faguiliu hybridmethodwithadaptivesubseriesclusteringandattentionbasedstackedresiduallstmsformultivariatetimeseriesforecasting AT yunshenglu hybridmethodwithadaptivesubseriesclusteringandattentionbasedstackedresiduallstmsformultivariatetimeseriesforecasting AT muqingcai hybridmethodwithadaptivesubseriesclusteringandattentionbasedstackedresiduallstmsformultivariatetimeseriesforecasting |